Image Generation Models - Parameters Reference

This page is auto-generated from model configurations. Last updated: 2026-03-13.

This reference lists all available image generation models and their parameters. Use these parameter names when calling the Generation API.

Models

Scenario

3D Color LUT

Model ID: model_scenario-postprocessing-lut

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-lut/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`lutStyle`	string	No	`teal_orange`	-	-	`teal_orange`, `kodak_portra`, `fuji_velvia`, `bleach_bypass`, `matrix_green`, `cgc_film_emulation_agfa_portrait_xps_160`, `cgc_film_emulation_fuji_astia_100f`, `cgc_film_emulation_fuji_eterna_3513`, `cgc_film_emulation_fuji_eterna_8563`, `cgc_film_emulation_fuji_provia_100f`, `cgc_film_emulation_fuji_sensia_100`, `cgc_film_emulation_fuji_superia_xtra_400`, `cgc_film_emulation_fuji_vivid_8543`, `cgc_film_emulation_kodak_ektachrome_64`, `cgc_film_emulation_kodak_professional_portra_400`, `cgc_film_emulation_kodak_vision_2383`, `cgc_film_emulation_lpp_tetrachrome_400`, `cgc_film_emulation_polaroid_600`, `cgc_log_to_rec709_alexa_logc`, `cgc_log_to_rec709_blackmagic_4.6k_film`, `cgc_log_to_rec709_blackmagic_4k_film`, `cgc_log_to_rec709_blackmagic_cinema_camera_film`, `cgc_log_to_rec709_canon_log`, `cgc_log_to_rec709_canon_log2`, `cgc_log_to_rec709_canon_log3`, `cgc_log_to_rec709_cinelike_d`, `cgc_log_to_rec709_cinestyle_s_curve`, `cgc_log_to_rec709_dji_inspire`, `cgc_log_to_rec709_gopro_protune`, `cgc_log_to_rec709_panasonic_v`, `cgc_log_to_rec709_redlogfilm`, `cgc_log_to_rec709_redwidegamut_log3g10`, `cgc_log_to_rec709_sony_slog2`, `cgc_log_to_rec709_sony_slog3_cine`, `cgc_log_to_rec709_sony_slog3`, `cgc_look_3strip`, `cgc_look_70s`, `cgc_look_amelie`, `cgc_look_aviator`, `cgc_look_blade_runner`, `cgc_look_bleach`, `cgc_look_brooklyn`, `cgc_look_celadon`, `cgc_look_chamoisee`, `cgc_look_cubanismo`, `cgc_look_drive`, `cgc_look_duotone`, `cgc_look_emulsion`, `cgc_look_enemy`, `cgc_look_enhance`, `cgc_look_fashion`, `cgc_look_glacier`, `cgc_look_godfather`, `cgc_look_grand_budapest`, `cgc_look_grime`, `cgc_look_grit`, `cgc_look_hannibal`, `cgc_look_her`, `cgc_look_mad_max`, `cgc_look_matrix_v1`, `cgc_look_matrix_v2`, `cgc_look_mint`, `cgc_look_moonrise_kingdom`, `cgc_look_ochre`, `cgc_look_punch`, `cgc_look_revenant`, `cgc_look_rhythm`, `cgc_look_seven`, `cgc_look_spy`, `cgc_look_stranger_things`, `cgc_look_summer`, `cgc_look_teal and orange`, `cgc_look_thriller`, `cgc_look_vinteo`, `cgc_look_wonder_woman`, `distant_land_basin`, `distant_land_boulder`, `distant_land_butte`, `distant_land_everest`, `distant_land_hopkins`, `distant_land_lochness`, `distant_land_oaxaca`, `distant_land_oslo`, `distant_land_phoenix`, `distant_land_pocatello`, `distant_land_prague`, `distant_land_reykjavik`, `distant_land_santafe`, `distant_land_seattle`, `distant_land_stillwater`, `distant_land_tahoe`, `distant_land_thames`, `pond5_arabica_12`, `pond5_ava_614`, `pond5_azrael_93`, `pond5_bourbon_64`, `pond5_byers_11`, `pond5_celluloid_01_fu_low`, `pond5_chemical_168`, `pond5_clayton_33`, `pond5_clouseau_54`, `pond5_cobi_3`, `pond5_contrail_35`, `pond5_cubicle_99`, `pond5_django_25`, `pond5_domingo_145`, `pond5_faded_47`, `pond5_folger_50`, `pond5_fusion_88`, `pond5_hyla_68`, `pond5_korben_214`, `pond5_lenox_340`, `pond5_lucky_64`, `pond5_mckinnon_75`, `pond5_milo_5`, `pond5_neon_770`, `pond5_paladin_1875`, `pond5_pasadena_21`, `pond5_pitaya_15`, `pond5_reeve_38`, `pond5_remy_24`, `pond5_sprocket_231`, `pond5_teigen_28`, `pond5_trent_18`, `pond5_tweed_71`, `pond5_vireo_37`, `pond5_zed_32`, `pond5_zeke_39`, `rec709_fujifilm_3510_d65`, `rec709_kodak_2383_d65`, `rec709_kodak_2393_d65`, `shutterstock_blue_architecture`, `shutterstock_blue_hour`, `shutterstock_cold_chrome`, `shutterstock_crisp_autumn`, `shutterstock_dark_and_somber`, `shutterstock_hard_boost`, `shutterstock_long_beach_morning`, `shutterstock_lush_green`, `shutterstock_magic_hour`, `shutterstock_natural_boost`, `shutterstock_orange_and_blue`, `shutterstock_soft_black_and_white`, `shutterstock_waves`	Style of grading to apply.
`lutIntensity`	number	No	`1`	0	1	-	Opacity of the LUT effect.

Blur

Model ID: model_scenario-postprocessing-blur

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-blur/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`blurType`	string	No	`gaussian`	-	-	`gaussian`, `kuwahara`	Type of blur to apply.
`blurRadius`	number	No	`3`	0	31	-	Blur radius.
`blurSigma`	number	No	`1`	0.1	10	-	Sigma for Gaussian blur.

Chromatic Aberration

Model ID: model_scenario-postprocessing-chromatic

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-chromatic/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`redShift`	number	No	`0`	-20	20	-	Red channel shift amount.
`greenShift`	number	No	`0`	-20	20	-	Green channel shift amount.
`blueShift`	number	No	`0`	-20	20	-	Blue channel shift amount.
`redDirection`	string	No	`horizontal`	-	-	`horizontal`, `vertical`	Red channel shift direction.
`greenDirection`	string	No	`horizontal`	-	-	`horizontal`, `vertical`	Green channel shift direction.
`blueDirection`	string	No	`horizontal`	-	-	`horizontal`, `vertical`	Blue channel shift direction.

Color Correction

Model ID: model_scenario-postprocessing-color-correction

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-color-correction/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`temperature`	number	No	`0`	-100	100	-	Color temperature adjustment (-100 to 100).
`brightness`	number	No	`0`	-100	100	-	Brightness adjustment (-100 to 100).
`contrast`	number	No	`0`	-100	100	-	Contrast adjustment (-100 to 100).
`saturation`	number	No	`0`	-100	100	-	Saturation adjustment (-100 to 100).
`gamma`	number	No	`1`	0.2	2.2	-	Gamma adjustment (0.2-2.2).
`exposure`	number	No	`0`	-5	5	-	Exposure adjustment (-5.0 to 5.0).
`shadows`	number	No	`0`	-100	100	-	Shadows adjustment (-100 to 100).
`highlights`	number	No	`0`	-100	100	-	Highlights adjustment (-100 to 100).
`shadowsHighlightsRadius`	number	No	`50`	0	100	-	Shadows/Highlights radius (0 to 100).

Crystallize

Model ID: model_scenario-postprocessing-crystallize

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-crystallize/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`crystallizeRadius`	number	No	`10`	1	100	-	Approximate size/number of the superpixel regions.

Cubism

Model ID: model_scenario-postprocessing-cubism

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-cubism/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`cubismTileSize`	number	No	`20`	1	100	-	Average tile size.
`cubismTileSaturation`	number	No	`2.5`	0	10	-	Tile saturation (expansion factor).

Desaturate

Model ID: model_scenario-postprocessing-desaturate

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-desaturate/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`desaturateMethod`	string	No	`luminance (Rec.709)`	-	-	`average`, `luminance (Rec.709)`, `luminance (Rec.601)`, `lightness`	Desaturation method.
`desaturateFactor`	number	No	`1`	0	1	-	Desaturation factor.

Dissolve

Model ID: model_scenario-postprocessing-dissolve

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-dissolve/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`dissolveImage`	file	No	-	-	-	-	Image to dissolve with.
`dissolveFactor`	number	No	`0.5`	0	1	-	Dissolve blend factor.

Dodge & Burn

Model ID: model_scenario-postprocessing-dodge-burn

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-dodge-burn/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`dodgeBurnMode`	string	No	`dodge`	-	-	`dodge`, `burn`, `dodge_and_burn`, `burn_and_dodge`, `color_dodge`, `color_burn`, `linear_dodge`, `linear_burn`	Dodge/Burn mode.
`dodgeBurnIntensity`	number	No	`0.5`	0	1	-	Dodge/Burn intensity.

Glow & Bloom

Model ID: model_scenario-postprocessing-glow

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-glow/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`glowRadius`	number	No	`5`	1	50	-	Glow blur radius.
`glowIntensity`	number	No	`1`	0	5	-	Glow intensity.

Grain

Model ID: model_scenario-postprocessing-grain

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-grain/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`grainProfile`	string	No	`kodak_portra_400`	-	-	`cine_still_800t`, `fuji_pro_400h`, `fuji_provia_100f`, `fuji_superia_400`, `fuji_velvia_50`, `ilford_hp5_plus`, `kodak_ektachrome_e100`, `kodak_ektar_100`, `kodak_gold_200`, `kodak_portra_400`, `kodak_tri_x_400`, `lomography_color_negative_400`, `modern`, `analog`, `cinematic`, `newspaper`, `vintage`, `bleach_bypass`, `infrared_bw`, `night_vision`, `sepia`, `old_fashion`	Film grain profile to use. Determines grain, color distribution, etc.
`grainColorTemp`	number	No	`6500`	2000	10000	-	Color temperature adjustment for grain.
`crossProcess`	boolean	No	`false`	-	-	-	Enable cross-processing effect.

Oilify

Model ID: model_scenario-postprocessing-oilify

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-oilify/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`oilifyRadius`	number	No	`4`	1	50	-	Radius of the oil painting effect (neighborhood size).
`oilifyIntensity`	number	No	`1`	1	20	-	Dynamic ratio of the oil painting effect (degree of abstraction).

Parabolize

Model ID: model_scenario-postprocessing-parabolize

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-parabolize/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`parabolizeCoeff`	number	No	`1`	-10	10	-	Parabolize coefficient.
`vertexX`	number	No	`0.5`	0	1	-	Vertex X position.
`vertexY`	number	No	`0.5`	0	1	-	Vertex Y position.

Posterize

Model ID: model_scenario-postprocessing-posterize

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-posterize/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`posterizeThreshold`	number	No	`0.5`	0	1	-	Posterize threshold.

Scenario Compose Image

Compose multiple images into a single image with layers, transforms, effects, and blending modes.

Model ID: model_scenario-compose-image

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-compose-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`layers`	inputs_array	Yes	-	-	-	-	Array of image layers to compose
`canvasMode`	string	No	`auto`	-	-	`auto`, `custom`	Canvas size mode. 'auto' computes from layers, 'custom' uses specified dimensions.
`canvasWidth`	number	No	-	1	7680	-	Output canvas width in pixels (required when canvas_mode='custom')
`canvasHeight`	number	No	-	1	4320	-	Output canvas height in pixels (required when canvas_mode='custom')
`backgroundColor`	string	No	`#000000`	-	-	-	Canvas background color (hex format #RRGGBB) or 'transparent'
`imageOutputFormat`	string	No	`png`	-	-	`png`, `jpg`, `webp`	Output image format
`imageQuality`	number	No	`95`	1	100	-	Image quality for lossy formats (jpg, webp). 1-100, higher is better.

Scenario Gemini Reframe

Model ID: model_scenario-gemini-reframe

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-gemini-reframe/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`prompt`	string	No	-	-	-	-	User prompt for image expansion
`aspectRatio`	string	No	`auto`	-	-	`21:9`, `16:9`, `4:3`, `3:2`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `auto`	Aspect ratio for the output canvas
`resolution`	string	No	`2K`	-	-	`1K`, `2K`, `4K`	Resolution for the output (1K, 2K, 4K)
`xStart`	number	No	-	0	-	-	Top-left x coordinate for crop bounds (in original image pixels)
`yStart`	number	No	-	0	-	-	Top-left y coordinate for crop bounds (in original image pixels)
`xEnd`	number	No	-	0	-	-	Bottom-right x coordinate for crop bounds (in original image pixels)
`yEnd`	number	No	-	0	-	-	Bottom-right y coordinate for crop bounds (in original image pixels)
`resizedWidth`	number	No	-	1	-	-	Width of source image after scaling (in output canvas pixels)
`resizedHeight`	number	No	-	1	-	-	Height of source image after scaling (in output canvas pixels)
`gridPositionX`	number	No	-	0	-	-	Grid offset x for image position (exclusive with position)
`gridPositionY`	number	No	-	0	-	-	Grid offset y for image position (exclusive with position)
`position`	string	No	-	-	-	`center`, `top`, `bottom`, `center-left`, `center-right`, `top-left`, `top-right`, `bottom-left`, `bottom-right`	Position enum (exclusive with grid_position): center, top, bottom, center-left, center-right, top-left, top-right, bottom-left, bottom-right
`seed`	number	No	-	0	2147483647	-	Seed for Gemini generation

Scenario Grid Maker

Model ID: model_scenario-grid-maker

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-grid-maker/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`images`	file_array	Yes	-	-	-	-	List of images to arrange in a grid
`columns`	number	No	`3`	1	20	-	Number of columns in the grid
`rows`	number	No	-	1	20	-	Number of rows in the grid. If not set, computed from images count and columns
`padding`	number	No	`0`	0	50	-	Padding between images in pixels
`backgroundColor`	string	No	`white`	-	-	-	Background color: hex string, 'transparent', 'black' or 'white'
`cellRatio`	string	No	`auto`	-	-	`9:16`, `2:3`, `3:4`, `1:1`, `5:4`, `4:3`, `3:2`, `16:9`, `21:9`, `auto`	Cell aspect ratio

Scenario Image Slicer

Model ID: model_scenario-image-slicer

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-image-slicer/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to slice
`xSubdivisions`	number	No	`2`	1	6	-	Number of subdivisions along the X axis
`ySubdivisions`	number	No	`2`	1	6	-	Number of subdivisions along the Y axis

Scenario Padding Remover

Automatically detects and removes uniform color borders/padding from images and videos.

Model ID: model_scenario-padding-remover

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-padding-remover/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to remove padding from
`color`	string	No	-	-	-	-	Hex color of the border to remove (e.g., 'FFFFFF' or '#FFFFFF'). If not specified, the color is auto-detected from the image corners.
`colorTolerance`	number	No	`0.4`	0	1	-	Color matching tolerance as a percentage (0.0-1.0). Higher values match more similar colors.
`width`	number	No	-	0	-	-	Width of the border to remove on all sides (in pixels). If not set, the border width is auto-detected.

Scenario Resize Image

Resize an image to a specified width and height or a maximum size while preserving aspect ratio.

Model ID: model_scenario-resize-image

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-resize-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image file to resize
`width`	number	No	-	1	-	-	Target width in pixels. If only width is specified, height is calculated to preserve aspect ratio.
`height`	number	No	-	1	-	-	Target height in pixels. If only height is specified, width is calculated to preserve aspect ratio.
`maxSizeMb`	number	No	-	0.1	-	-	Maximum output file size in megabytes. The file will be resized iteratively to meet this constraint while preserving aspect ratio.
`preserveAspectRatio`	boolean	No	`true`	-	-	-	Whether to preserve the original aspect ratio. When True (default), the output fits within the specified dimensions. When False, the output is stretched to exactly match the specified dimensions.

Scenario Texture Converter

Converts an image texture to PBR texture maps (height, normal, smoothness, metallic, edge, AO).

Model ID: model_sc-texture-converter

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sc-texture-converter/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`texture`	file	Yes	-	-	-	-	Image to convert
`raised`	number	No	`0.5`	0	1	-	How raised is the surface? 0 is flat like water, 1 is like a very rough rock
`shiny`	number	No	`0.5`	0	1	-	How shiny is the surface? 0 is like a matte surface, 1 is like a diamond
`polished`	number	No	`0.5`	0	1	-	How polished is the surface? 0 is like a rough surface, 1 is like a mirror
`angular`	number	No	`0.5`	0	1	-	How angular is the surface? 0 is like a sphere, 1 is like a mechanical object
`invert`	boolean	No	`false`	-	-	-	Invert the relief
`defaultParameters`	boolean	No	`false`	-	-	-	If true, use the default parameters

Sharpen

Model ID: model_scenario-postprocessing-sharpen

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-sharpen/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`sharpenMode`	string	No	`basic`	-	-	`basic`, `smart`, `cas`	Type of sharpening to apply.
`preserveEdges`	number	No	`0.75`	0	1	-	Edge preservation factor.
`sharpenRadius`	number	No	`1`	1	15	-	Sharpen radius (for basic mode).
`sharpenAlpha`	number	No	`1`	0.1	5	-	Sharpen strength (for basic mode).
`smartSharpenStrength`	number	No	`5`	0	25	-	Smart sharpen strength.
`smartSharpenRatio`	number	No	`0.5`	0	1	-	Smart sharpen blend ratio.
`noiseRadius`	number	No	`7`	1	25	-	Noise radius for smart sharpen.
`casAmount`	number	No	`0.8`	0	1	-	CAS sharpening amount.

Solarize

Model ID: model_scenario-postprocessing-solarize

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-solarize/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`solarizeThreshold`	number	No	`0.5`	0	1	-	Solarize threshold.

Tint

Model ID: model_scenario-postprocessing-tint

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-tint/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`tintMode`	string	No	`sepia`	-	-	`sepia`, `red`, `green`, `blue`, `cyan`, `magenta`, `yellow`, `purple`, `orange`, `warm`, `cool`, `lime`, `navy`, `vintage`, `rose`, `teal`, `maroon`, `peach`, `lavender`, `olive`	Tint color mode.
`tintStrength`	number	No	`1`	0.1	1	-	Tint strength.

Vignette

Model ID: model_scenario-postprocessing-vignette

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_scenario-postprocessing-vignette/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`vignetteStrength`	number	No	`0.5`	0	1	-	Vignette strength.

Academia

Physic Edit

Physics-aware image editing with realistic refraction, material changes, and deformations.

Model ID: model_physic-edit

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_physic-edit/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image to edit with physics-aware transformations.
`prompt`	string	Yes	-	-	-	-	Editing instructions describing the physical transformation to apply.
`negativePrompt`	string	No	-	-	-	-	Description of unwanted elements in the output.
`numInferenceSteps`	number	No	`40`	1	50	-	Number of denoising steps.
`cfgScale`	number	No	`4`	1	20	-	Classifier-free guidance scale.
`seed`	number	No	-	0	2147483647	-	Random seed for reproducibility.

VecGlypher

Generate SVG glyphs directly from text prompts with controllable typography and styling.

Model ID: model_vecglypher

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_vecglypher/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	The target text to generate as vector glyphs.
`styleDescription`	string	No	`italic style, 400 weight, serif, text, elegant`	-	-	-	Typography style guidance such as weight, style, and category.
`outputSize`	number	No	`512`	64	4096	-	Maximum output dimension in pixels while preserving aspect ratio.
`fillColor`	string	No	`black`	-	-	-	SVG/CSS fill color for generated glyphs.
`strokeColor`	string	No	-	-	-	-	Optional outline color for generated glyph paths.
`strokeWidth`	number	No	`1`	0.1	50	-	Outline width in SVG units when a stroke color is set.
`temperature`	number	No	`0.1`	0	2	-	Sampling temperature.
`topP`	number	No	`0.95`	0	1	-	Top-p (nucleus) sampling parameter.
`topK`	number	No	`5`	-1	100	-	Top-k sampling parameter.
`repetitionPenalty`	number	No	`1`	0	2	-	Penalty to reduce repeated SVG path segments.
`maxTokens`	number	No	`8192`	256	16384	-	Maximum number of tokens to generate.
`seed`	number	No	-	0	2147483647	-	Random seed for reproducibility.

VecGlypher Image to SVG

Generate SVG glyphs from a text prompt while matching the style of reference glyph images.

Model ID: model_vecglypher-image-to-svg

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_vecglypher-image-to-svg/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	-	-	-	-	Reference glyph images to match style from (1 to 8 images).
`prompt`	string	Yes	-	-	-	-	Target text to generate as vector glyphs.
`outputSize`	number	No	`512`	64	4096	-	Maximum output dimension in pixels while preserving aspect ratio.
`fillColor`	string	No	`black`	-	-	-	SVG/CSS fill color for generated glyphs.
`strokeColor`	string	No	-	-	-	-	Optional outline color for generated glyph paths.
`strokeWidth`	number	No	`1`	0.1	50	-	Outline width in SVG units when a stroke color is set.
`temperature`	number	No	`0.1`	0	2	-	Sampling temperature.
`topP`	number	No	`0.95`	0	1	-	Top-p (nucleus) sampling parameter.
`topK`	number	No	`5`	-1	100	-	Top-k sampling parameter.
`repetitionPenalty`	number	No	`1`	0	2	-	Penalty to reduce repeated SVG path segments.
`maxTokens`	number	No	`8192`	256	16384	-	Maximum number of tokens to generate.
`seed`	number	No	-	0	2147483647	-	Random seed for reproducibility.

Z-Image

Z-Image - Highest quality text-to-image and image-to-image generation

Model ID: model_z-image

Capabilities: txt2img, img2img, controlnet

LLM Markdown: https://app.scenario.com/api/models/model_z-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`negativePrompt`	string	No	-	-	-	-	Text prompt for what to avoid in the image
`image`	file	No	-	-	-	-	Source image for img2img transformation
`strength`	number	No	`0.6`	0	1	-	How much to transform the reference image. 0 means no change, 1 means complete transformation
`controlImage`	file_array	No	-	-	-	-	Control images to use as input (edge, depth, or pose)
`controlnetConditioningScale`	number	No	`0.75`	0	1	-	The scale of the controlnet conditioning
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	Number of inference steps.
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`5`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Z-Image Turbo

Z-Image Turbo - Fast text-to-image and image-to-image generation model

Model ID: model_z-image-turbo

Capabilities: txt2img, img2img, controlnet

LLM Markdown: https://app.scenario.com/api/models/model_z-image-turbo/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`negativePrompt`	string	No	-	-	-	-	Text prompt for what to avoid in the image
`image`	file	No	-	-	-	-	Source image for img2img transformation. Cannot be used with ControlNet.
`strength`	number	No	`0.75`	0	1	-	How much to transform the reference image. 0 means no change, 1 means complete transformation
`controlImage`	file_array	No	-	-	-	-	Control images to use as input (edge, depth, or pose). Cannot be used with Reference Image.
`controlnetConditioningScale`	number	No	`0.7`	0	1	-	The scale of the controlnet conditioning
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`9`	1	100	-	Number of inference steps.
`width`	number	No	-	128	2048	-	Width of the generated image
`height`	number	No	-	128	2048	-	Height of the generated image
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Z-Image Turbo ControlNet

Generate images from text and edge, depth or pose images using Z-Image Turbo, Tongyi-MAI's super-fast 6B model.

Model ID: model_z-image-turbo-controlnet

Capabilities: controlnet

LLM Markdown: https://app.scenario.com/api/models/model_z-image-turbo-controlnet/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`negativePrompt`	string	No	-	-	-	-	Text prompt for what to avoid in the image
`controlImage`	file_array	Yes	-	-	-	-	Control images to use as input (edge, depth, or pose)
`controlnetConditioningScale`	number	No	`0.75`	0	1	-	The scale of the controlnet conditioning
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`9`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`1`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Alibaba

Qwen Edit

The latest Qwen-Image’s iteration with improved multi-image editing, single-image consistency, and native support for ControlNet

Model ID: model_qwen-image-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	-	-	-	-	Images to use as reference.
`prompt`	string	Yes	-	-	-	-	Text instruction on how to edit the given image. If you are using a LoRA, use the LoRA instruction instead.
`lora`	string	No	-	-	-	`dx8152/qwen-edit-2509-multiple-angles`, `dx8152/Qwen-Edit-2509-Multi-Angle-Lighting`, `tarn59/apply_texture_qwen_image_edit_2509`, `autoweeb/Qwen-Image-Edit-2509-Photo-to-Anime`, `tlennon-ie/qwen-edit-skin`, `rsshekhawat/Qwen-Edit-3DChibi-LoRA`, `dx8152/Qwen-Image-Edit-2509-Fusion`, `lovis93/next-scene-qwen-image-lora-2509`, `dx8152/Qwen-Image-Edit-2509-Light_restoration`, `dx8152/Qwen-Image-Edit-2509-White_to_Scene`, `flymy-ai/qwen-image-edit-inscene-lora`, `vafipas663/Qwen-Edit-2509-Upscale-LoRA`, `peteromallet/Qwen-Image-Edit-InSubject`, `FoxBaze/Try_On_Qwen_Edit_Lora_Alpha`, `https://huggingface.co/Alissonerdx/BFS-Best-Face-Swap/blob/main/bfs_head_v3_qwen_image_edit_2509.safetensors`, `oumoumad/Qwen-Edit-2509-Material-transfer`, `oumoumad/Qwen-Edit-2509-Extract-materials`, `oumoumad/Apply-Vinyl-Wrap`, ``	Choose a LoRA optimized for Qwen Edit to guide the model's editing style or transformations. (See Knowledge Base for details.
`loraScale`	number	No	`1`	0	4	-	Adjust the influence of the selected Qwen Edit LoRA
`aspectRatio`	string	No	`match_input_image`	-	-	`match_input_image`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Aspect ratio for the generated image
`goFast`	boolean	No	`false`	-	-	-	True runs the 8 steps Lightning preset
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Qwen Edit - Camera Control

Camera-aware edits for Qwen/Qwen-Image-Edit-2509 with Lightning + multi-angle LoRA

Model ID: model_qwen-edit-multiangle

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-edit-multiangle/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image to edit.
`prompt`	string	No	-	-	-	-	Optional text instruction appended after the camera directive.
`rotateDegrees`	number	No	`0`	-90	90	-	Camera orbit angle in degrees. Positive values move the camera to the left, while negative values move it to the right.
`moveForward`	number	No	`0`	0	10	-	Move the camera forward (zoom in). Higher values push towards a close-up.
`verticalTilt`	number	No	`0`	-1	1	-	Vertical camera tilt. -1 = top-down, 1 = low-angle view.
`useWideAngle`	boolean	No	`false`	-	-	-	Switch to a wide-angle lens instruction.
`aspectRatio`	string	No	`match_input_image`	-	-	`match_input_image`, `16:9`, `4:3`, `1:1`, `3:4`, `9:16`	Aspect ratio for the generated image
`loraScale`	number	No	`1.25`	0	4	-	Relative strength for the multi-angle LoRA.
`goFast`	boolean	No	`false`	-	-	-	Run faster predictions with additional optimizations.

Qwen Edit 2509

Qwen Image Edit 2509 - Image-to-image editing model (September 2025 version)

Model ID: model_qwen-image-edit-2509

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-edit-2509/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`referenceImages`	file_array	Yes	-	-	-	-	Reference images for editing
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Qwen Edit 2511

Qwen Image Edit 2511 - Image-to-image editing model (November 2025 version)

Model ID: model_qwen-image-edit-2511

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-edit-2511/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`referenceImages`	file_array	Yes	-	-	-	-	Reference images for editing
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Qwen Edit Multiangle 2511

Generate same scene from different angles with Qwen image Edit 2511 and the LoRA Multiple Angles

Model ID: model_qwen-edit-multiangle-2511

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-edit-multiangle-2511/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`images`	file_array	Yes	-	-	-	-	Input image to edit
`horizontalAngle`	number	No	`0`	0	360	-	Horizontal angle (azimuth) in degrees: 0°=front, 90°=right side, 180°=back, 270°=left, 360°=front view again
`verticalAngle`	number	No	`0`	-30	90	-	Vertical angle (elevation) in degrees: -30°=low-angle, 0°=eye-level, 90°=bird's-eye
`zoom`	number	No	`5`	0	10	-	Zoom - Distance level: 0=wide shot, 5=medium, 10=close-up
`loraScale`	number	No	`1.5`	0	4	-	LoRA scale controls camera control effect strength
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	50	-	Number of inference steps (higher = better quality, slower)
`guidanceScale`	number	No	`4.5`	1	20	-	Guidance scale for generation (higher = closer to prompt)
`acceleration`	string	No	`none`	-	-	`none`, `regular`	Acceleration mode for faster generation
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Qwen Edit Plus

Qwen Image Edit Plus- Image-to-image editing model

Model ID: model_qwen-image-edit

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-edit/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`referenceImages`	file	Yes	-	-	-	-	Input image for editing
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Qwen Image

Qwen Image - Text-to-image and image-to-image generation model

Model ID: model_qwen-image

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`image`	file	No	-	-	-	-	Input image for img2img
`strength`	number	No	`0.6`	0	1	-	Lower values adhere more closely to the image, while higher values allow for more creative freedom
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of steps for the generation
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Qwen Image 2512

Qwen Image 2512 - Enhanced text-to-image and image-to-image generation model with improved resolution support

Model ID: model_qwen-image-2512

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-2512/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`image`	file	No	-	-	-	-	Input image for img2img
`strength`	number	No	`0.6`	0	1	-	Lower values adhere more closely to the image, while higher values allow for more creative freedom
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	Number of denoising steps. Use less steps for faster generation.
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

Qwen Image Layered

Generate images with separate foreground, background, and shadow layers for easy editing and compositing

Model ID: model_qwen-image-layered

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_qwen-image-layered/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	No	-	-	-	-	Image to be converted into a layered image.
`description`	string	No	`auto`	-	-	-	Text description of the input image. Use 'auto' for auto captioning.
`numLayers`	number	No	`4`	2	8	-	Number of layers to generate.
`goFast`	boolean	No	`true`	-	-	-	Enable this option to run faster generations with additional optimizations (8 steps Lightning preset)
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

BFL

FLUX Kontext Edit

Flux Kontext for advanced image editing and generation

Model ID: model_flux-kontext-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_flux-kontext-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs or URLs.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`referenceImages`	file_array	Yes	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing or generation
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`aspectRatio`	string	No	`auto`	-	-	`21:9`, `16:9`, `3:2`, `4:3`, `1:1`, `2:3`, `3:4`, `9:16`, `9:21`, `auto`	Aspect ratio for the generated image
`quality`	string	No	`high`	-	-	`high`, `medium`	Generation quality
`guidanceScale`	number	No	`3.5`	1	10	-	How closely to follow the prompt (1.0-10.0)
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results (single-image inference). Leave blank to use a random seed.

FLUX.1 Dev

FLUX.1 Dev - High-quality text-to-image generation model

Model ID: model_bfl-flux-1-dev

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-1-dev/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA or composition model ID. If a composition is provided, the loras and lorasScale arrays will be automatically populated from the composition's concepts. If a LoRA is provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If provided, this will override the LoRAs extracted from the composition (when modelId is a composition). If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`image`	file	No	-	-	-	-	Input image for img2img
`strength`	number	No	`0.8`	0.01	1	-	Lower values adhere more closely to the image, while higher values allow for more creative freedom. (Higher values are recommended for this model)
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate.
`numInferenceSteps`	number	No	`28`	1	50	-	The number of denoising steps
`width`	number	No	`1104`	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	`832`	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`3.5`	0	10	-	Controls how closely the generated image follows the prompt (ignored for schnell)
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.1 Krea Dev

An opinionated text-to-image model from Black Forest Labs in collaboration with Krea that excels in photorealism. Creates images that avoid the oversaturated 'AI look'.

Model ID: model_flux-krea-dev

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_flux-krea-dev/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	No	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:21`, `9:16`, `2:3`, `3:4`, `4:5`, `1:1`, `3:2`, `4:3`, `5:4`, `16:9`, `21:9`	Image aspect ratio. Ignored if you have a reference image.
`image`	file	No	-	-	-	-	Use a reference image to guide your generation. The aspect ratio of your output will match this image
`promptStrength`	number	No	`0.8`	0	1	-	Lower values adhere more closely to the image, while higher values allow for more creative freedom. (Higher values are recommended for this model)
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate.
`steps`	number	No	`28`	1	50	-	The number of steps for the generation
`guidance`	number	No	`3`	0	10	-	Higher values adhere more closely to the prompt, while lower values allow for more creative freedom.
`megapixels`	string	No	`1`	-	-	`1`, `0.25`	Approximate number of megapixels for generated image
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

FLUX.1 Schnell

FLUX.1 Schnell - Fast text-to-image generation model

Model ID: model_bfl-flux-1-schnell

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-1-schnell/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA or composition model ID. If a composition is provided, the loras and lorasScale arrays will be automatically populated from the composition's concepts. If a LoRA is provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If provided, this will override the LoRAs extracted from the composition (when modelId is a composition). If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights, overriding the composition scales.
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`image`	file	No	-	-	-	-	Reference image
`strength`	number	No	`0.8`	0.01	1	-	Lower values adhere more closely to the image, while higher values allow for more creative freedom. (Higher values are recommended for this model)
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate.
`numInferenceSteps`	number	No	`4`	1	10	-	The number of denoising steps
`width`	number	No	`1104`	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	`832`	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`3.5`	0	10	-	Controls how closely the generated image follows the prompt (ignored for schnell)
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.1.1 Pro

Faster, better FLUX Pro. Text-to-image model with excellent image quality, prompt adherence, and output diversity.

Model ID: model_bfl-flux-1-1-pro

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-1-1-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`imagePrompt`	file	No	-	-	-	-	Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the Image prompt.
`aspectRatio`	string	No	`1:1`	-	-	`16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for the generated image
`promptUpsampling`	boolean	No	`false`	-	-	-	Automatically modify the prompt for more creative generation
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

FLUX.1.1 Pro Ultra

FLUX1.1 [pro] in ultra and raw modes. Images are up to 4 megapixels. Use raw mode for realism.

Model ID: model_bfl-flux-1-1-pro-ultra

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-1-1-pro-ultra/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`imagePrompt`	file	No	-	-	-	-	Image to use with Flux Redux. This is used together with the text prompt to guide the generation towards the composition of the image_prompt. Must be jpeg, png, gif, or webp.
`aspectRatio`	string	No	`1:1`	-	-	`21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `9:21`	Aspect ratio for the generated image
`raw`	boolean	No	`false`	-	-	-	Generate less processed, more natural-looking images
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

FLUX.2 Dev

FLUX.2 Dev - High-quality text-to-image and image-to-image model

Model ID: model_bfl-flux-2-dev

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-dev/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	Reference images
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.2 Flex Edit

FLUX.2 Flex is designed for maximum versatility and ease of use. It prioritizes adaptability, allowing fast generation, broad compatibility, and reliable results

Model ID: model_bfl-flux-2-flex-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-flex-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`1:1`	-	-	`match_input_image`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for the generated image. When aspect ratio is 'Match Input Image', use 'Match Input Image' to match the input image's aspect ratio.
`resolution`	string	No	`1 MP`	-	-	`match_input_image`, `0.5 MP`, `1 MP`, `2 MP`, `4 MP`	Resolution in megapixels. When aspect ratio is 'Auto (Match Input)', use 'Auto (Match Input)' to match the input image's resolution (clamped to 0.5-4 MP).
`promptUpsampling`	boolean	No	`false`	-	-	-	Automatically modify the prompt for more creative generation
`steps`	number	No	`30`	1	50	-	Number of steps to run the model for. Fewer steps means faster generation, at the expensive of output quality. 30 steps is sufficient for most prompts.
`guidance`	number	No	`4.5`	1.5	10	-	Guidance scale. Higher values mean more guidance, lower values mean more creative generation.
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

FLUX.2 Klein 4b

FLUX.2 Klein 4b - Efficient text-to-image and image-to-image model

Model ID: model_bfl-flux-2-klein-4b

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-klein-4b/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	Reference images
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`4`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`1`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.2 Klein 9b

FLUX.2 Klein 9b - Efficient text-to-image and image-to-image model

Model ID: model_bfl-flux-2-klein-9b

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-klein-9b/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	Reference images for img2img
`numOutputs`	number	No	`4`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`4`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`1`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.2 Klein Base 4b

FLUX.2 Klein Base 4b - Efficient text-to-image and image-to-image model

Model ID: model_bfl-flux-2-klein-4b-base

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-klein-4b-base/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	Reference images
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.2 Klein Base 9b

FLUX.2 Klein Base 9b - Efficient text-to-image and image-to-image model

Model ID: model_bfl-flux-2-klein-9b-base

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-klein-9b-base/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`modelId`	model	No	-	-	-	-	A single LoRA model ID. If provided, it will be added to the loras array.
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs. If modelId is a LoRA and this is not provided, it will be automatically populated with the modelId.
`lorasScale`	number_array	No	-	0	2	-	Scales for the LoRA weights
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	Reference images for img2img
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`numInferenceSteps`	number	No	`28`	1	100	-	The number of denoising steps
`width`	number	No	-	128	2048	-	The width of the generated images, must be a multiple of 16
`height`	number	No	-	128	2048	-	The height of the generated images, must be a multiple of 16
`guidance`	number	No	`4`	1	10	-	Controls how closely the generated image follows the prompt
`seed`	number	No	-	0	2147483647	-	Used to reproduce previous results

FLUX.2 Max Edit

Model ID: model_bfl-flux-2-max-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-max-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`4:3`	-	-	`match_input_image`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for the generated image. Use 'Auto (Match Input)' to match the first input image's aspect ratio.
`resolution`	string	No	`1 MP`	-	-	`match_input_image`, `0.5 MP`, `1 MP`, `2 MP`, `4 MP`	Resolution in megapixels. Up to 4 MP is possible, but 2 MP or below is recommended. The maximum image size is 2048x2048, which means that high-resolution images may not respect the resolution if aspect ratio is not 1:1. When Aspect ratio is 'Auto (Match Input)', use Auto to match the input image's resolution (clamped to 0.5-4 MP).
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

FLUX.2 Pro Edit

FLUX.2 Pro is the highest-fidelity, flagship version of the FLUX.2 lineup

Model ID: model_bfl-flux-2-pro-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-pro-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`1:1`	-	-	`match_input_image`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for the generated image. When aspect ratio is 'Match Input Image', use 'Match Input Image' to match the input image's aspect ratio.
`resolution`	string	No	`1 MP`	-	-	`match_input_image`, `0.5 MP`, `1 MP`, `2 MP`, `4 MP`	Resolution in megapixels. When aspect ratio is 'Auto (Match Input)', use 'Auto (Match Input)' to match the input image's resolution (clamped to 0.5-4 MP).
`promptUpsampling`	boolean	No	`false`	-	-	-	Automatically modify the prompt for more creative generation
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

FLUX.2 Turbo Edit

Image-to-image editing with FLUX.2 [turbo] from Black Forest Labs. Precise modifications using natural language descriptions and hex color control—all at turbo speed.

Model ID: model_bfl-flux-2-turbo-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_bfl-flux-2-turbo-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`imageSize`	string	No	`landscape_4_3`	-	-	`portrait_16_9`, `portrait_4_3`, `square_hd`, `landscape_4_3`, `landscape_16_9`	Image size for the generated image.
`guidance`	number	No	`2.5`	1.5	10	-	Guidance scale. Higher values mean more guidance, lower values mean more creative generation.
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate.
`promptUpsampling`	boolean	No	`false`	-	-	-	Automatically modify the prompt for more creative generation
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

Scenario Skybox Upscale

Model ID: model_sc-upscale-flux-skybox

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sc-upscale-flux-skybox/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to upscale
`upscaleFactor`	number	No	`2`	2	8	-	Upscale factor
`prompt`	string	No	-	-	-	-	Prompt
`imagePrompt`	file_array	No	-	-	-	-	Upload up to 4 images to guide the style of the output.
`imagePromptStrength`	number	No	`0.6`	0	1	-	Higher fidelity keeps the enhanced image's style closely aligned with the style images
`controlnetConditioningScale`	number	No	`0.5`	0	1	-	Higher values better preserve the structure of the input image.
`strength`	number	No	`0.6`	0	1	-	Higher values introduce more imaginative elements to the output image.
`numInferenceSteps`	number	No	`28`	1	50	-	The number of steps for the generation
`detailsEnable`	boolean	No	`true`	-	-	-	Enhances fine details in the output image.
`baseModel`	string	No	`FLUX.1-dev`	-	-	`FLUX.1-dev`, `FLUX.1-Krea-dev`	Use FLUX.1-dev for stylized images, and FLUX.1-Krea-dev for realistic images.
`seed`	number	No	-	0	2147483647	-	Seed used for reproduction

Scenario Texture Upscale

Model ID: model_sc-upscale-flux-texture

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sc-upscale-flux-texture/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to upscale
`upscaleFactor`	number	No	`2`	2	8	-	Upscale factor
`preset`	string	No	`balanced`	-	-	`precise`, `balanced`, `creative`	Select a preset to apply a set of parameters
`loras`	model_array	No	``	-	-	-	List of one or more LoRA model IDs or URLs.
`lorasScale`	number_array	No	``	-	-	-	Scales for the LoRA weights
`prompt`	string	No	-	-	-	-	Prompt
`imagePrompt`	file_array	No	-	-	-	-	Upload up to 4 images to guide the style of the output.
`imagePromptStrength`	number	No	`0.6`	0	1	-	Higher fidelity keeps the enhanced image's style closely aligned with the style images
`controlnetConditioningScale`	number	No	`0.4`	0	1	-	Higher values better preserve the structure of the input image.
`strength`	number	No	`0.4`	0	1	-	Higher values introduce more imaginative elements to the output image.
`numInferenceSteps`	number	No	`28`	1	50	-	The number of steps for the generation
`detailsEnable`	boolean	No	`true`	-	-	-	Enhances fine details in the output image.
`baseModel`	string	No	`FLUX.1-dev`	-	-	`FLUX.1-dev`, `FLUX.1-Krea-dev`	Use FLUX.1-dev for stylized images, and FLUX.1-Krea-dev for realistic images.
`seed`	number	No	-	0	2147483647	-	Seed used for reproduction

Bytedance

Dreamina 3.1

ByteDance's creativity-focused model for stylized outputs.

Model ID: model_bytedance-dreamina-3-1

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_bytedance-dreamina-3-1/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`4:3`	-	-	`9:21`, `9:16`, `2:3`, `3:4`, `1:1`, `3:2`, `4:3`, `16:9`, `21:9`, `custom`	Image aspect ratio. Set to 'custom' to specify width and height.
`resolution`	string	No	`2K`	-	-	`1K`, `2K`	Image resolution quality
`width`	number	No	`1328`	512	3024	-	Image width (only used when aspect_ratio is 'custom')
`height`	number	No	`1328`	512	3024	-	Image height (only used when aspect_ratio is 'custom')
`seed`	number	No	-	-	-	-	Use a seed for reproducible results. Leave blank to use a random seed.

Seedream 3

Realism-driven image generator with strong lighting control.

Model ID: model_bytedance-seedream-3

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_bytedance-seedream-3/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`width`	number	No	`2048`	512	2048	-	Image width
`height`	number	No	`2048`	512	2048	-	Image height
`seed`	number	No	-	-	-	-	Use a custom seed for targeted results (single-image inference)

Seedream 4.0 Edit

Model ID: model_bytedance-seedream-4-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bytedance-seedream-4-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	``	-	-	-	Input image(s) for image-to-image generation. List of 1-14 images for single or multi-reference generation.
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`size`	string	No	`4K`	-	-	`4K`, `2K`, `1K`	Output resolution. 1K for low quality, 2K for medium quality, 4K for high quality.
`aspectRatio`	string	No	`auto`	-	-	`1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, `21:9`, `auto`	Image aspect ratio. 'Auto' preserves the original aspect ratio but does not upscale image resolution.
`sequentialImageGeneration`	string	No	`disabled`	-	-	`disabled`, `auto`	Off: always generates one image. On: The model may generate a set of related images (story steps, variations, or alternatives), up to your chosen Max Images parameter.
`maxImages`	number	No	`1`	1	15	-	The maximum number of images the model can generate in one sequence. Total image count (input +generated) cannot exceed 15.

Seedream 4.5 Edit

Model ID: model_bytedance-seedream-4-5-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bytedance-seedream-4-5-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	``	-	-	-	Input image(s) for image-to-image generation. List of 1-10 images for single or multi-reference generation.
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`size`	string	No	`4K`	-	-	`4K`, `2K`	Image resolution: 2K (2048px), 4K (4096px).
`aspectRatio`	string	No	`auto`	-	-	`1:1`, `4:3`, `3:4`, `16:9`, `9:16`, `3:2`, `2:3`, `21:9`, `auto`	Image aspect ratio. 'Auto' preserves the original aspect ratio but does not upscale image resolution.
`sequentialImageGeneration`	string	No	`disabled`	-	-	`disabled`, `auto`	Off: always generates one image. On: The model may generate a set of related images (story steps, variations, or alternatives), up to your chosen Max Images parameter.
`maxImages`	number	No	`1`	1	15	-	The maximum number of images the model can generate in one sequence. Total image count (input + generated) cannot exceed 15.

Seedream 5.0 Lite

Model ID: model_bytedance-seedream-5-0-lite

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_bytedance-seedream-5-0-lite/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	``	-	-	-	Input image(s) for image-to-image generation.
`aspectRatio`	string	No	`1:1`	-	-	`match_input_image`, `21:9`, `16:9`, `4:3`, `3:2`, `1:1`, `2:3`, `3:4`, `9:16`	Image aspect ratio. 'Auto' preserves the original aspect ratio but does not upscale image resolution.
`width`	number	No	`2048`	1024	4704	-	Custom image width (only used when size is set to 'Custom'). Range: 1024-4096 pixels.
`height`	number	No	`2048`	1024	4096	-	Custom image height (only used when size is set to 'Custom'). Range: 1024-4096 pixels.
`sequentialImageGeneration`	string	No	`disabled`	-	-	`disabled`, `auto`	Off: always generates one image. On: The model may generate a set of related images (story steps, variations, or alternatives), up to your chosen Max Images parameter.
`maxImages`	number	No	`1`	1	15	-	The maximum number of images the model can generate in one sequence. Total image count (input + generated) cannot exceed 15.

Google

Gemini 2.5 Flash

Nano-banana is Google's state-of-the-art image generation and editing model

Model ID: model_google-gemini-2-5-flash-image-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_google-gemini-2-5-flash-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation/editing
`aspectRatio`	string	No	`auto`	-	-	`21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `auto`	Aspect ratio for the generated image
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Gemini 3.0 Pro

Nano Banana Pro (a.k.a Nano Banana 2) is Google's new state-of-the-art image generation and editing model

Model ID: model_google-gemini-pro-image-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_google-gemini-pro-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`aspectRatio`	string	No	`auto`	-	-	`21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `auto`	Aspect ratio for the generated image
`resolution`	string	No	`2K`	-	-	`1K`, `2K`, `4K`	Resolution for the generated image
`useGoogleSearch`	boolean	No	`false`	-	-	-	Use Google Search to find more information about the prompt
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Gemini 3.1 Flash (Nano Banana 2)

Nano Banana 2 combines Pro capabilities with Flash-tier speed — edit and generate images using multimodal understanding, up to 14 reference images, and natural language instructions for context-aware edits that preserve composition, lighting, and style coherence.

Model ID: model_google-gemini-3-1-flash

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_google-gemini-3-1-flash/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation/editing
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`aspectRatio`	string	No	`auto`	-	-	`21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`, `auto`	Aspect ratio for the generated image
`resolution`	string	No	`1K`	-	-	`512`, `1K`, `2K`, `4K`	Resolution for the generated image
`useGoogleSearch`	boolean	No	`false`	-	-	-	Use Google Search to find more information about the prompt
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Imagen 3

Google's highest quality text-to-image model, capable of generating images with detail, rich lighting and beauty

Model ID: model_imagen3

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_imagen3/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `3:4`, `1:1`, `4:3`, `16:9`	Image aspect ratio

Imagen 3 Fast

A faster and cheaper Imagen 3 model, for when price or speed are more important than final image quality.

Model ID: model_imagen3-fast

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_imagen3-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `3:4`, `1:1`, `4:3`, `16:9`	Image aspect ratio

Imagen 4

Google's Imagen 4 flagship model.

Model ID: model_imagen4

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_imagen4/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `3:4`, `1:1`, `4:3`, `16:9`	Image aspect ratio

Imagen 4 Fast

Use this fast version of Imagen 4 when speed and cost are more important than quality.

Model ID: model_imagen4-fast

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_imagen4-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `3:4`, `1:1`, `4:3`, `16:9`	Image aspect ratio

Imagen 4 Ultra

Use this ultra version of Imagen 4 when quality matters more than speed and cost.

Model ID: model_imagen4-ultra

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_imagen4-ultra/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `3:4`, `1:1`, `4:3`, `16:9`	Image aspect ratio

Ideogram

Ideogram Character

Model ID: model_ideogram-character

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_ideogram-character/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`renderingSpeed`	string	No	`Default`	-	-	`Default`, `Turbo`, `Quality`	Turbo for faster and cheaper generation, quality for higher quality and more expensive generation, default for balanced.
`characterReferenceImage`	file	Yes	-	-	-	-	An image to use as a character reference.
`styleType`	string	No	`Auto`	-	-	`Auto`, `Fiction`, `Realistic`	The character style type. Auto, Fiction, or Realistic.
`aspectRatio`	string	No	`4:3`	-	-	`1:3`, `1:2`, `2:3`, `3:4`, `4:5`, `9:16`, `10:16`, `1:1`, `3:2`, `4:3`, `5:4`, `16:10`, `16:9`, `2:1`, `3:1`	Aspect ratio. Ignored if a resolution or inpainting image is given.
`resolution`	string	No	`None`	-	-	`None`, `1536x512`, `1472x576`, `1408x528`, `1408x704`, `1280x720`, `1280x768`, `1024x768`, `1024x1024`, `768x1024`, `832x1472`, `704x1408`, `512x1536`	Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.
`image`	file	No	-	-	-	-	An image file to use for inpainting. You must also use a mask.
`mask`	file	No	-	-	-	-	A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.
`seed`	number	No	-	-	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Ideogram V3 Balanced

Ideogram v3 balanced: Balance speed, quality and cost. Ideogram v3 creates images with stunning realism, creative designs, and consistent styles.

Model ID: model_ideogram-v3-balanced

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-balanced/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`1:3`, `1:2`, `2:3`, `3:4`, `4:5`, `9:16`, `10:16`, `1:1`, `5:4`, `4:3`, `3:2`, `16:10`, `16:9`, `2:1`, `3:1`	Aspect ratio. Ignored if a resolution or inpainting image is given.
`resolution`	string	No	`None`	-	-	`None`, `512x1536`, `576x1408`, `640x1344`, `704x1344`, `768x1344`, `832x1216`, `896x1152`, `960x1024`, `1024x1024`, `1088x960`, `1152x896`, `1216x832`, `1280x768`, `1344x704`, `1408x640`, `1472x576`, `1536x512`	Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.
`magicPromptOption`	string	No	`Auto`	-	-	`Auto`, `On`, `Off`	Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages.
`image`	file	No	-	-	-	-	An image file to use for inpainting. You must also use a mask.
`mask`	file	No	-	-	-	-	A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.
`styleReferenceImages`	file_array	No	-	-	-	-	A list of images to use as style references.
`styleType`	string	No	`None`	-	-	`None`, `Auto`, `General`, `Realistic`, `Design`	The styles help define the specific aesthetic of the image you want to generate.
`stylePreset`	string	No	`None`	-	-	`None`, `80s Illustration`, `90s Nostalgia`, `Abstract Organic`, `Analog Nostalgia`, `Art Brut`, `Art Deco`, `Art Poster`, `Aura`, `Avant Garde`, `Bauhaus`, `Blueprint`, `Blurry Motion`, `Bright Art`, `C4D Cartoon`, `Children's Book`, `Collage`, `Coloring Book I`, `Coloring Book II`, `Cubism`, `Dark Aura`, `Doodle`, `Double Exposure`, `Dramatic Cinema`, `Editorial`, `Emotional Minimal`, `Ethereal Party`, `Expired Film`, `Flat Art`, `Flat Vector`, `Forest Reverie`, `Geo Minimalist`, `Glass Prism`, `Golden Hour`, `Graffiti I`, `Graffiti II`, `Halftone Print`, `High Contrast`, `Hippie Era`, `Iconic`, `Japandi Fusion`, `Jazzy`, `Long Exposure`, `Magazine Editorial`, `Minimal Illustration`, `Mixed Media`, `Monochrome`, `Nightlife`, `Oil Painting`, `Old Cartoons`, `Paint Gesture`, `Pop Art`, `Retro Etching`, `Riviera Pop`, `Spotlight 80s`, `Stylized Red`, `Surreal Collage`, `Travel Poster`, `Vintage Geo`, `Vintage Poster`, `Watercolor`, `Weird`, `Woodblock Print`	The style preset to use for the image generation.
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Ideogram V3 Quality

The highest quality Ideogram v3 model. v3 creates images with stunning realism, creative designs, and consistent styles.

Model ID: model_ideogram-v3-quality

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-quality/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`1:3`, `1:2`, `2:3`, `3:4`, `4:5`, `9:16`, `10:16`, `1:1`, `5:4`, `4:3`, `3:2`, `16:10`, `16:9`, `2:1`, `3:1`	Aspect ratio. Ignored if a resolution or inpainting image is given.
`resolution`	string	No	`None`	-	-	`None`, `512x1536`, `576x1408`, `640x1344`, `704x1344`, `768x1344`, `832x1216`, `896x1152`, `960x1024`, `1024x1024`, `1088x960`, `1152x896`, `1216x832`, `1280x768`, `1344x704`, `1408x640`, `1472x576`, `1536x512`	Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.
`magicPromptOption`	string	No	`Auto`	-	-	`Auto`, `On`, `Off`	Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages.
`image`	file	No	-	-	-	-	An image file to use for inpainting. You must also use a mask.
`mask`	file	No	-	-	-	-	A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.
`styleReferenceImages`	file_array	No	-	-	-	-	A list of images to use as style references.
`styleType`	string	No	`None`	-	-	`None`, `Auto`, `General`, `Realistic`, `Design`	The styles help define the specific aesthetic of the image you want to generate.
`stylePreset`	string	No	`None`	-	-	`None`, `80s Illustration`, `90s Nostalgia`, `Abstract Organic`, `Analog Nostalgia`, `Art Brut`, `Art Deco`, `Art Poster`, `Aura`, `Avant Garde`, `Bauhaus`, `Blueprint`, `Blurry Motion`, `Bright Art`, `C4D Cartoon`, `Children's Book`, `Collage`, `Coloring Book I`, `Coloring Book II`, `Cubism`, `Dark Aura`, `Doodle`, `Double Exposure`, `Dramatic Cinema`, `Editorial`, `Emotional Minimal`, `Ethereal Party`, `Expired Film`, `Flat Art`, `Flat Vector`, `Forest Reverie`, `Geo Minimalist`, `Glass Prism`, `Golden Hour`, `Graffiti I`, `Graffiti II`, `Halftone Print`, `High Contrast`, `Hippie Era`, `Iconic`, `Japandi Fusion`, `Jazzy`, `Long Exposure`, `Magazine Editorial`, `Minimal Illustration`, `Mixed Media`, `Monochrome`, `Nightlife`, `Oil Painting`, `Old Cartoons`, `Paint Gesture`, `Pop Art`, `Retro Etching`, `Riviera Pop`, `Spotlight 80s`, `Stylized Red`, `Surreal Collage`, `Travel Poster`, `Vintage Geo`, `Vintage Poster`, `Watercolor`, `Weird`, `Woodblock Print`	The style preset to use for the image generation.
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Ideogram V3 Turbo

Turbo is the fastest and cheapest Ideogram v3. v3 creates images with stunning realism, creative designs, and consistent styles

Model ID: model_ideogram-v3-turbo

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_ideogram-v3-turbo/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Describe your image
`aspectRatio`	string	No	`4:3`	-	-	`1:3`, `1:2`, `2:3`, `3:4`, `4:5`, `9:16`, `10:16`, `1:1`, `5:4`, `4:3`, `3:2`, `16:10`, `16:9`, `2:1`, `3:1`	Aspect ratio. Ignored if a resolution or inpainting image is given.
`resolution`	string	No	`None`	-	-	`None`, `512x1536`, `576x1408`, `640x1344`, `704x1344`, `768x1344`, `832x1216`, `896x1152`, `960x1024`, `1024x1024`, `1088x960`, `1152x896`, `1216x832`, `1280x768`, `1344x704`, `1408x640`, `1472x576`, `1536x512`	Resolution. Overrides aspect ratio. Ignored if an inpainting image is given.
`magicPromptOption`	string	No	`Auto`	-	-	`Auto`, `On`, `Off`	Magic Prompt will interpret your prompt and optimize it to maximize variety and quality of the images generated. You can also use it to write prompts in different languages.
`image`	file	No	-	-	-	-	An image file to use for inpainting. You must also use a mask.
`mask`	file	No	-	-	-	-	A black and white image. Black pixels are inpainted, white pixels are preserved. The mask will be resized to match the image size.
`styleReferenceImages`	file_array	No	-	-	-	-	A list of images to use as style references.
`styleType`	string	No	`None`	-	-	`None`, `Auto`, `General`, `Realistic`, `Design`	The styles help define the specific aesthetic of the image you want to generate.
`stylePreset`	string	No	`None`	-	-	`None`, `80s Illustration`, `90s Nostalgia`, `Abstract Organic`, `Analog Nostalgia`, `Art Brut`, `Art Deco`, `Art Poster`, `Aura`, `Avant Garde`, `Bauhaus`, `Blueprint`, `Blurry Motion`, `Bright Art`, `C4D Cartoon`, `Children's Book`, `Collage`, `Coloring Book I`, `Coloring Book II`, `Cubism`, `Dark Aura`, `Doodle`, `Double Exposure`, `Dramatic Cinema`, `Editorial`, `Emotional Minimal`, `Ethereal Party`, `Expired Film`, `Flat Art`, `Flat Vector`, `Forest Reverie`, `Geo Minimalist`, `Glass Prism`, `Golden Hour`, `Graffiti I`, `Graffiti II`, `Halftone Print`, `High Contrast`, `Hippie Era`, `Iconic`, `Japandi Fusion`, `Jazzy`, `Long Exposure`, `Magazine Editorial`, `Minimal Illustration`, `Mixed Media`, `Monochrome`, `Nightlife`, `Oil Painting`, `Old Cartoons`, `Paint Gesture`, `Pop Art`, `Retro Etching`, `Riviera Pop`, `Spotlight 80s`, `Stylized Red`, `Surreal Collage`, `Travel Poster`, `Vintage Geo`, `Vintage Poster`, `Watercolor`, `Weird`, `Woodblock Print`	The style preset to use for the image generation.
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

LongCat

LongCat Image Editing

LongCat image Edit is a 6B parameter image editing model excelling at multilingual text rendering, photorealism and deployment efficiency.

Model ID: model_longcat-image-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_longcat-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImage`	file	Yes	-	-	-	-	Reference image to use for editing.
`prompt`	string	Yes	-	-	-	-	A textual prompt to guide model generation.
`numInferenceSteps`	number	No	`28`	1	50	-	Number of inference steps.
`guidanceScale`	number	No	`4.5`	1	20	-	Guidance scale. Higher values adhere more closely to the prompt.
`numOutputs`	number	No	`1`	1	4	-	Number of images to generate.
`seed`	number	No	-	0	2147483647	-	Seed for random number generation.

Luma Labs

Luma Photon

Model ID: model_luma-photon

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_luma-photon/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`4:3`	-	-	`9:21`, `9:16`, `3:4`, `1:1`, `4:3`, `16:9`, `21:9`	Aspect ratio of the generated image
`imageReferenceUrl`	file	No	-	-	-	-	Use a reference image to guide your generation.
`imageReferenceWeight`	number	No	`0.85`	0	1	-	Influence of the reference image. Larger values will make the reference image have a stronger influence on the generated image.
`styleReferenceUrl`	file	No	-	-	-	-	Use a style image to influence the visual style of your generation.
`styleReferenceWeight`	number	No	`0.85`	0	1	-	Influence of the style reference image. Larger values will make the style reference image have a stronger influence on the generated image.
`characterReferenceUrl`	file	No	-	-	-	-	Use a character image to guide your generation.
`seed`	number	No	-	-	-	-	Use a custom seed for targeted results (single-image inference)

Luma Photon Flash

Model ID: model_luma-photon-flash

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_luma-photon-flash/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`4:3`	-	-	`9:21`, `9:16`, `3:4`, `1:1`, `4:3`, `16:9`, `21:9`	Aspect ratio of the generated image
`imageReferenceUrl`	file	No	-	-	-	-	Use a reference image to guide your generation.
`imageReferenceWeight`	number	No	`0.85`	0	1	-	Influence of the reference image. Larger values will make the reference image have a stronger influence on the generated image.
`styleReferenceUrl`	file	No	-	-	-	-	Use a style image to influence the visual style of your generation.
`styleReferenceWeight`	number	No	`0.85`	0	1	-	Influence of the style reference image. Larger values will make the style reference image have a stronger influence on the generated image.
`characterReferenceUrl`	file	No	-	-	-	-	Use a character image to guide your generation.
`seed`	number	No	-	-	-	-	Use a custom seed for targeted results (single-image inference)

MiniMax

Minimax Image 01

Model ID: model_minimax-image-01

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_minimax-image-01/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for generation
`aspectRatio`	string	No	`4:3`	-	-	`9:16`, `2:3`, `3:4`, `1:1`, `3:2`, `4:3`, `16:9`, `21:9`	Image aspect ratio
`numOutputs`	number	No	`1`	1	9	-	Number of images to generate
`promptOptimizer`	boolean	No	`true`	-	-	-	Use prompt optimizer
`subjectReference`	file	No	-	-	-	-	An optional character reference image (human face) to use as the subject in the generated image(s).

OpenAI

GPT Image

OpenAI's GPT Image 1 model for image editing and generation

Model ID: model_openai-gpt-image-1-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_openai-gpt-image-1-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`aspectRatio`	string	No	`auto`	-	-	`auto`, `1:1`, `3:2`, `2:3`	Aspect ratio for the generated image
`inputFidelity`	string	No	`high`	-	-	`low`, `high`	Preserve details from input images
`quality`	string	No	`high`	-	-	`high`, `medium`, `low`	Generation quality
`background`	string	No	`auto`	-	-	`transparent`, `opaque`, `auto`	Background transparency

GPT Image 1.5

OpenAI's GPT Image 1.5 model for image editing

Model ID: model_openai-gpt-image-1-5-editing

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_openai-gpt-image-1-5-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	No	-	-	-	-	Reference images for style or content guidance
`prompt`	string	Yes	-	-	-	-	Text prompt for image editing
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`aspectRatio`	string	No	`auto`	-	-	`auto`, `1:1`, `3:2`, `2:3`	Aspect ratio for the generated image
`inputFidelity`	string	No	`high`	-	-	`low`, `high`	Preserve details from input images
`quality`	string	No	`high`	-	-	`high`, `medium`, `low`	Generation quality
`background`	string	No	`auto`	-	-	`transparent`, `opaque`, `auto`	Background transparency

Photoroom

Photoroom Background Removal

Remove backgrounds from images with high-quality results using Photoroom's background removal service.

Model ID: model_photoroom-background-removal

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-background-removal/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`backgroundColor`	string	No	-	-	-	-	Background color (hex without # or HTML color name). No value means transparent.
`shadowMode`	string	No	-	-	-	``, `soft`, `hard`, `floating`	Automatically generates a realistic shadow to 'ground' your subject. Choose Soft for a professional studio look, Hard for direct sunlight, or Floating to create a 3D hover effect.

Photoroom Background Replacer

Replace backgrounds in images with AI-generated backgrounds using Photoroom's background replacer service.

Model ID: model_photoroom-background-replacer

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-background-replacer/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`prompt`	string	No	-	-	-	-	Text prompt for background generation
`referenceImage`	file	No	-	-	-	-	Reference image for background guidance
`referenceImageGuidance`	number	No	`0.6`	0	1	-	How closely the generated background matches the reference image (0.0 to 1.0)
`seed`	number	No	-	0	-	-	Seed for background generation

Photoroom Expand

Expand images using AI to extend the canvas beyond the original image boundaries using Photoroom's expand service.

Model ID: model_photoroom-expand

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-expand/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`outputWidth`	number	Yes	`1024`	1	4096	-	Output width in pixels
`outputHeight`	number	Yes	`1024`	1	4096	-	Output height in pixels
`seed`	number	No	-	0	-	-	Seed for expand generation

Photoroom Relighting

Adjust lighting in images using AI to enhance or modify the lighting conditions using Photoroom's relighting service.

Model ID: model_photoroom-relighting

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-relighting/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`lightingMode`	string	No	`auto`	-	-	`auto`, `preserve-hue-and-saturation`	Lighting mode for the image

Photoroom Text Remover

Remove text from images using AI to clean up text overlays and watermarks using Photoroom's text remover service.

Model ID: model_photoroom-text-remover

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-text-remover/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`mode`	string	Yes	`artificial`	-	-	`artificial`, `natural`, `all`	Controls which text is removed from images. Remove artificial overlays like logos and watermarks, natural scene text like signs or clothing prints, or both for a fully text free image.

Photoroom Uncrop

Uncrop images using AI to restore and extend cropped areas beyond the original image boundaries using Photoroom's uncrop service.

Model ID: model_photoroom-uncrop

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_photoroom-uncrop/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image file
`seed`	number	No	-	0	-	-	Seed for uncrop generation

Pixa

Pixa Background Removal

Fast, ultra high-quality background removal from images. Perfect for e-commerce and image editing workflows.

Model ID: model_pixa-background-removal

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_pixa-background-removal/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image
`outputFormat`	string	No	`rgba`	-	-	`rgba`, `alpha`	Output format for the processed image

Pruna AI

P-Image

Model ID: model_p-image

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_p-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation.
`width`	number	No	`1216`	256	1440	-	Width of the generated image. Only used when Aspect Ratio is 'custom'. Must be a multiple of 16.
`height`	number	No	`832`	256	1440	-	Height of the generated image. Only used when Aspect Ratio is 'custom'. Must be a multiple of 16.
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation.

P-Image Edit

A sub 1 second cheap multi-image editing model built for production use cases.

Model ID: model_p-image-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_p-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	-	-	-	-	Images to use as a reference. For editing task, provide the main image as the first image.
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation. Make sure to describe your edit task clearly. You can refer to the images as 'image 1' and 'image 2' and so on.
`turbo`	boolean	No	`true`	-	-	-	If turned on, the model will run faster with additional optimizations. For complicated tasks, it is recommended to turn this off.
`aspectRatio`	string	No	`match_input_image`	-	-	`16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`, `match_input_image`	Aspect ratio for the generated image. `match_input_image` will match the aspect ratio of the first image.
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation.

Recraft AI

Recraft V3

Recraft V3 is a text-to-image model that generates images from text descriptions.

Model ID: model_recraft-v3

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v3/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	No	-	-	-	-	Describe your image
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `2:3`, `3:4`, `3:5`, `4:5`, `5:7`, `1:1`, `5:4`, `4:3`, `7:5`, `3:2`, `5:3`, `16:9`, `2:1`, `9:16`	Image aspect ratio
`size`	string	No	`1365x1024`	-	-	`1024x2048`, `1024x1820`, `1024x1707`, `1024x1536`, `1024x1434`, `1024x1365`, `1024x1280`, `1024x1024`, `1280x1024`, `1365x1024`, `1434x1024`, `1536x1024`, `1707x1024`, `1820x1024`, `2048x1024`	Width and height of the generated image. Size is ignored if an aspect ratio is set.
`style`	string	No	`any`	-	-	`any`, `realistic_image`, `digital_illustration`, `digital_illustration/pixel_art`, `digital_illustration/hand_drawn`, `digital_illustration/grain`, `digital_illustration/infantile_sketch`, `digital_illustration/2d_art_poster`, `digital_illustration/handmade_3d`, `digital_illustration/hand_drawn_outline`, `digital_illustration/engraving_color`, `digital_illustration/2d_art_poster_2`, `realistic_image/b_and_w`, `realistic_image/hard_flash`, `realistic_image/hdr`, `realistic_image/natural_light`, `realistic_image/studio_portrait`, `realistic_image/enterprise`, `realistic_image/motion_blur`	Style of the generated image.

Recraft V3 - SVG Creator

Recraft V3 SVG is a text-to-image model that generates SVG images from text descriptions.

Model ID: model_recraft-v3-svg

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v3-svg/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	No	-	-	-	-	Describe your image
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `2:3`, `3:4`, `3:5`, `4:5`, `5:7`, `1:1`, `5:4`, `4:3`, `7:5`, `3:2`, `5:3`, `16:9`, `2:1`, `9:16`	Image aspect ratio
`size`	string	No	`1365x1024`	-	-	`1024x2048`, `1024x1536`, `1024x1365`, `1024x1280`, `1024x1024`, `1280x1024`, `1365x1024`, `1536x1024`, `2048x1024`	Width and height of the generated image. Size is ignored if an aspect ratio is set.
`style`	string	No	`any`	-	-	`any`, `engraving`, `line_art`, `line_circuit`, `linocut`	Style of the generated image.

Recraft V4

Recraft's image generation model, built around design taste. Strong prompt accuracy, art-directed composition, and integrated text rendering. Fast and cost-efficient at standard resolution.

Model ID: model_recraft-v4

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v4/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `9:16`, `6:10`, `2:3`, `10:14`, `3:4`, `4:5`, `1:1`, `5:4`, `4:3`, `14:10`, `3:2`, `16:9`, `2:1`	Aspect ratio of the generated image
`size`	string	No	`1024x1024`	-	-	`768x1536`, `768x1344`, `832x1344`, `832x1280`, `896x1280`, `896x1216`, `896x1152`, `1024x1024`, `1152x896`, `1216x896`, `1280x896`, `1280x832`, `1344x768`, `1536x768`	Width and height of the generated image. Size is ignored if an aspect ratio is set.

Recraft V4 Pro

Recraft's image generation modelat ~2048px resolution. Same design taste and prompt accuracy as V4, with higher resolution for print-ready and large-scale work.

Model ID: model_recraft-v4-pro

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v4-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `9:16`, `6:10`, `2:3`, `10:14`, `3:4`, `4:5`, `1:1`, `5:4`, `4:3`, `14:10`, `3:2`, `16:9`, `2:1`	Aspect ratio of the generated image
`size`	string	No	`2048x2048`	-	-	`1536x3072`, `1536x2688`, `1664x2688`, `1664x2560`, `1792x2560`, `1792x2432`, `1792x2304`, `2048x2048`, `2304x1792`, `2432x1792`, `2560x1792`, `2560x1664`, `2688x1536`, `3072x1536`	Width and height of the generated image. Size is ignored if an aspect ratio is set.

Recraft V4 Pro SVG

Generate detailed SVG vector graphics from text prompts. Recraft V4 Pro's design taste with more geometric detail and finer paths — clean layers, editable output, and scalable to any size.

Model ID: model_recraft-v4-pro-svg

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v4-pro-svg/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `9:16`, `6:10`, `2:3`, `10:14`, `3:4`, `4:5`, `1:1`, `5:4`, `4:3`, `14:10`, `3:2`, `16:9`, `2:1`	Aspect ratio of the generated image
`size`	string	No	`2048x2048`	-	-	`1536x3072`, `1536x2688`, `1664x2688`, `1664x2560`, `1792x2560`, `1792x2432`, `1792x2304`, `2048x2048`, `2304x1792`, `2432x1792`, `2560x1792`, `2560x1664`, `2688x1536`, `3072x1536`	Width and height of the generated image. Size is ignored if an aspect ratio is set.

Recraft V4 SVG

Generate production-ready SVG vector images from text prompts. Recraft V4's design taste applied to vector output — clean geometry, structured layers, and editable paths.

Model ID: model_recraft-v4-svg

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-v4-svg/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`Not set`	-	-	`Not set`, `1:2`, `9:16`, `6:10`, `2:3`, `10:14`, `3:4`, `4:5`, `1:1`, `5:4`, `4:3`, `14:10`, `3:2`, `16:9`, `2:1`	Aspect ratio of the generated image
`size`	string	No	`1024x1024`	-	-	`768x1536`, `768x1344`, `832x1344`, `832x1280`, `896x1280`, `896x1216`, `896x1152`, `1024x1024`, `1152x896`, `1216x896`, `1280x896`, `1280x832`, `1344x768`, `1536x768`	Width and height of the generated image. Size is ignored if an aspect ratio is set.

Recraft Vectorize

Converts a given raster image to SVG format using Recraft model.

Model ID: model_recraft-vectorize

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_recraft-vectorize/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImage`	file	Yes	-	-	-	-	The image to convert to SVG format. 5mb max size.

Retro-Diffusion

Retro Diffusion Animation

A dedicated animation model featuring specialized motion-aware generation, perfect for sprite sequences.

Model ID: model_retrodiffusion-animation

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-animation/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for generation
`image`	file	No	-	-	-	-	Input image for image-to-image generation or reference. Will be converted to RGB without transparency.
`style`	string	No	`four_angle_walking`	-	-	`four_angle_walking`, `walking_and_idle`, `small_sprites`, `vfx`	Style to apply to the generated image
`width`	number	No	`48`	24	96	-	Animation width. four_angle_walking and walking_and_idle only support 48. small_sprites only supports 32. vfx supports 24-96.
`height`	number	No	`48`	24	96	-	Animation height. four_angle_walking and walking_and_idle only support 48. small_sprites only supports 32. vfx supports 24-96.
`returnSpritesheet`	boolean	No	`false`	-	-	-	Return animation as a spritesheet PNG instead of animated GIF
`bypassPromptExpansion`	boolean	No	`false`	-	-	-	Disable automatic prompt expansion
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

Retro Diffusion Plus

A premium pixel-art generation model designed for exceptional quality, rich detail, and stylistic accuracy.

Model ID: model_retrodiffusion-plus

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-plus/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for generation
`style`	string	No	`default`	-	-	`default`, `retro`, `watercolor`, `textured`, `cartoon`, `ui_element`, `item_sheet`, `character_turnaround`, `environment`, `isometric`, `isometric_asset`, `topdown_map`, `topdown_asset`, `classic`, `topdown_item`, `low_res`, `mc_item`, `mc_texture`, `skill_icon`	Style to apply to the generated image
`image`	file	No	-	-	-	-	Input image for image-to-image generation or reference. Will be converted to RGB without transparency.
`strength`	number	No	`0.8`	0	1	-	Prompt strength in image-to-image generation. Higher values give closer adherence to the prompt, and lower values use more information from the input image. Only used when Reference Image is provided.
`inputPalette`	file	No	-	-	-	-	Reference palette image to guide color choices
`width`	number	No	`256`	16	384	-	Image width
`height`	number	No	`256`	16	384	-	Image height
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`removeBg`	boolean	No	`false`	-	-	-	Remove background to create transparent images
`tileX`	boolean	No	`false`	-	-	-	Enable seamless tiling on X axis
`tileY`	boolean	No	`false`	-	-	-	Enable seamless tiling on Y axis
`bypassPromptExpansion`	boolean	No	`false`	-	-	-	Disable automatic prompt expansion
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation

Retro Diffusion Tile

A specialized model built for generating seamless, top-down tilemaps with perfect grid alignment and terrain coherence.

Model ID: model_retrodiffusion-tile

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_retrodiffusion-tile/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text prompt for generation
`image`	file	No	-	-	-	-	Reference image for image-to-image generation or reference. Will be converted to RGB without transparency.
`style`	string	No	`tileset`	-	-	`tileset`, `tileset_advanced`, `single_tile`, `tile_variation`, `tile_object`, `scene_object`	Style to apply to the generated image tileset: Create full tilesets from a simple prompt describing the textures or environment, using a simple set of "wang" style combinations tileset_advanced: Full tilesets from two prompts and/or textures, using a simple set of "wang" style combinations single_tile: Detailed single tile texture for creating full tilesets or surfaces tile_variation: Texture variations of the provided tile image tile_object: Small assets for placing on sections of tiles scene_object: Large assets for placing on tileset maps
`width`	number	No	`32`	16	384	-	Tile width (for tilesets, this is the size of each individual tile, not the output image)
`height`	number	No	`32`	16	384	-	Tile height (for tilesets, this is the size of each individual tile, not the output image)
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`bypassPromptExpansion`	boolean	No	`false`	-	-	-	Disable automatic prompt expansion
`seed`	number	No	-	-	-	-	Random seed. Set for reproducible generation
`extraImage`	file	No	-	-	-	-	Extra reference image for advanced tileset generation
`extraPrompt`	string	No	-	-	-	-	Extra prompt for advanced tileset generation

Reve AI

Reve Create

Model ID: model_reve-create

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_reve-create/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	No	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`4:3`	-	-	`16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`	The desired aspect ratio of the generated image
`seed`	number	No	-	-	-	-	Use a seed for reproducible results. Leave blank to use a random seed.

Reve Remix

Model ID: model_reve-remix

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_reve-remix/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	No	-	-	-	-	Text prompt for image generation
`referenceImages`	file_array	No	-	-	-	-	List of 1-4 image files to remix from
`aspectRatio`	string	No	`4:3`	-	-	`16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`	The desired aspect ratio of the generated image

Runway ML

Runway Gen 4

Model ID: model_runway-gen4-image-editing

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_runway-gen4-image-editing/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImages`	file_array	Yes	``	-	-	-	Up to 3 reference images.
`prompt`	string	Yes	-	-	-	-	Text prompt for image generation
`aspectRatio`	string	No	`1920:1080`	-	-	`2112:912`, `1808:768`, `1680:720`, `1920:1080`, `1360:768`, `1280:720`, `1440:1080`, `1168:880`, `960:720`, `1024:1024`, `1080:1080`, `1080:1440`, `720:960`, `720:720`, `720:1280`, `1080:1920`	Aspect ratio for the generated image
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Sourceful

Riverflow 2.0 Fast

Agentic image model optimized for high-quality, fast generations.

Model ID: model_sourceful-riverflow-2-0-fast

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-fast/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Generation instruction
`referenceImages`	file_array	No	-	-	-	-	Reference images to edit.
`superResolutionRefs`	file_array	No	-	-	-	-	Optional reference images for detail fix
`resolution`	string	No	`1K`	-	-	`1K`, `2K`	Target resolution
`aspectRatio`	string	No	`auto`	-	-	`auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for output.
`fontUrls`	string_array	No	-	-	-	-	Optional font URLs (ttf/otf/woff/woff2). Up to 2.
`fontTexts`	string_array	No	-	-	-	-	Text strings matching font_urls (≤300 chars each).
`transparency`	boolean	No	`false`	-	-	-	Enable transparent background when supported.
`enhancePrompt`	boolean	No	`false`	-	-	-	Let model enhance the instruction.
`maxIterations`	number	No	`3`	1	3	-	Number of internal reasoning iterations.

Riverflow 2.0 Pro

Agentic image model optimized for robust, high-precision generations supporting font control

Model ID: model_sourceful-riverflow-2-0-pro

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Generation instruction
`referenceImages`	file_array	No	-	-	-	-	Reference images to edit.
`superResolutionRefs`	file_array	No	-	-	-	-	Optional reference images for detail fix
`resolution`	string	No	`1K`	-	-	`1K`, `2K`, `4K`	Target resolution
`aspectRatio`	string	No	`auto`	-	-	`auto`, `21:9`, `16:9`, `3:2`, `4:3`, `5:4`, `1:1`, `4:5`, `3:4`, `2:3`, `9:16`	Aspect ratio for output.
`fontUrls`	string_array	No	-	-	-	-	Optional font URLs (ttf/otf/woff/woff2). Up to 2.
`fontTexts`	string_array	No	-	-	-	-	Text strings matching font_urls (≤300 chars each).
`transparency`	boolean	No	`false`	-	-	-	Enable transparent background when supported.
`enhancePrompt`	boolean	No	`false`	-	-	-	Let model enhance the instruction.
`maxIterations`	number	No	`3`	1	3	-	Number of internal reasoning iterations.

Riverflow 2.0 REFSR

Render product images with 100% accuracy and environmental blending

Model ID: model_sourceful-riverflow-2-0-refsr

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sourceful-riverflow-2-0-refsr/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`referenceImage`	file	Yes	-	-	-	-	The base image to apply super resolution to.
`superResolutionReferences`	file_array	Yes	-	-	-	-	Reference images for super resolution guidance.

Tencent

Hunyuan Image V3

Leverage the state-of-the-art capabilities of Hunyuan Image 3.0 to generate visual content that effectively conveys the messaging of your written material.

Model ID: model_hunyuan-image-v3

Capabilities: txt2img

LLM Markdown: https://app.scenario.com/api/models/model_hunyuan-image-v3/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	A textual prompt to guide model generation.
`negativePrompt`	string	No	-	-	-	-	The negative prompt to guide the image generation away from certain concepts.
`imageSize`	string	No	`landscape_4_3`	-	-	`portrait_16_9`, `portrait_4_3`, `square`, `square_hd`, `landscape_4_3`, `landscape_16_9`	The size of the generated image.
`numOutputs`	number	No	`1`	1	4	-	Number of Images to generate
`numInferenceSteps`	number	No	`50`	1	50	-	The number of inference steps.
`guidanceScale`	number	No	`3.5`	1	20	-	Higher values adhere more closely to the input prompt, while lower values allow for more creative freedom.
`enablePromptExpansion`	boolean	No	`false`	-	-	-	Enable prompt expansion
`seed`	number	No	-	0	2147483647	-	Use a seed for reproducible results. Leave blank to use a random seed.

Vision Cortex

VTracer

Converts raster images to SVG format using VisionCortex VTracer with customizable vectorization parameters.

Model ID: model_visioncortex-vtracer

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_visioncortex-vtracer/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to vectorize
`presetName`	string	No	`poster`	-	-	`bw`, `poster`, `photo`, `custom`	Preset configuration. When using a preset, custom parameters are ignored.
`colorMode`	string	No	`color`	-	-	`color`, `binary`	Color mode: 'color' or 'binary'. Only used with preset is Custom.
`colorPrecision`	number	No	`6`	1	8	-	Number of significant bits for RGB channels (1-8). Higher values preserve more color detail. Phoenix param: colorPrecision. Only used with preset is Custom.
`layerDifference`	number	No	`16`	0	255	-	Color difference between gradient layers (0-255). Phoenix param: layerDifference. Only used with preset is Custom.
`hierarchical`	string	No	`stacked`	-	-	`stacked`, `cutout`	Hierarchical clustering mode: 'stacked' or 'cutout'. Only used with preset is Custom.
`mode`	string	No	`spline`	-	-	`spline`, `polygon`, `pixel`, `none`	Curve fitting mode: 'spline' (smooth curves), 'polygon' (straight lines), 'pixel' (pixelated), or 'none'. Only used with preset='custom'.
`filterSpeckle`	number	No	`4`	0	128	-	Discard patches smaller than X pixels. Only used with preset is Custom.
`cornerThreshold`	number	No	`60`	0	180	-	Minimum angle (degrees) to be considered a corner (0-180). Only used with preset is Custom.
`lengthThreshold`	number	No	`4`	3.5	10	-	Maximum segment length for curve smoothing (3.5-10). Only used with preset is Custom.
`spliceThreshold`	number	No	`45`	0	180	-	Minimum angle displacement for splines (0-180 degrees). Only used with preset is Custom.

xAI

Grok Imagine Image

Generate and edit images using xAI's Grok model, powered by Aurora — supports text-to-image generation and image editing with multiple aspect ratios and batch output up to 10 images

Model ID: model_xai-grok-imagine-image

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_xai-grok-imagine-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text description of the image to generate, or desired edits when a source image is provided
`referenceImages`	file_array	No	``	-	-	-	Reference images to edit. When provided, the prompt describes the desired edits. Aspect ratio is ignored in editing mode.
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`aspectRatio`	string	No	`1:1`	-	-	`2:1`, `16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`, `1:2`, `auto`	Aspect ratio for the generated image. Ignored when editing a source image.

Grok Imagine Image Pro

Generate and edit high-resolution images using xAI's Grok Pro model, powered by Aurora — supports text-to-image generation and image editing with up to 2K resolution, multiple aspect ratios, and batch output up to 10 images

Model ID: model_xai-grok-imagine-image-pro

Capabilities: txt2img, img2img

LLM Markdown: https://app.scenario.com/api/models/model_xai-grok-imagine-image-pro/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`prompt`	string	Yes	-	-	-	-	Text description of the image to generate, or desired edits when a source image is provided
`referenceImages`	file_array	No	``	-	-	-	Reference images to edit. When provided, the prompt describes the desired edits. Aspect ratio is ignored in editing mode.
`numOutputs`	number	No	`1`	1	10	-	Number of images to generate
`resolution`	string	No	`2k`	-	-	`1k`, `2k`	Output resolution for the generated image. 2K is only available with the Pro model.
`aspectRatio`	string	No	`1:1`	-	-	`2:1`, `16:9`, `3:2`, `4:3`, `1:1`, `3:4`, `2:3`, `9:16`, `1:2`, `auto`	Aspect ratio for the generated image. Ignored when editing a source image.

Models

Scenario

Academia

Alibaba

BFL

Bytedance

Google

Ideogram

LongCat

Luma Labs

Meta

MiniMax

OpenAI

Photoroom

Pixa

Pruna AI

Recraft AI

Retro-Diffusion

Reve AI

Runway ML

Sourceful

Tencent

Vision Cortex

xAI

Scenario

3D Color LUT

Blur

Chromatic Aberration

Color Correction

Crystallize

Cubism

Desaturate

Dissolve

Dodge & Burn

Glow & Bloom

Grain

Oilify

Parabolize

Posterize

Scenario Compose Image

Scenario Gemini Reframe

Scenario Grid Maker

Scenario Image Slicer

Scenario Padding Remover

Scenario Resize Image

Scenario Texture Converter

Sharpen

Solarize

Tint

Vignette

Academia

Physic Edit

VecGlypher

VecGlypher Image to SVG

Z-Image

Z-Image Turbo

Z-Image Turbo ControlNet

Alibaba

Qwen Edit

Qwen Edit - Camera Control

Qwen Edit 2509

Qwen Edit 2511

Qwen Edit Multiangle 2511

Qwen Edit Plus

Qwen Image

Qwen Image 2512

Qwen Image Layered

BFL

FLUX Kontext Edit

FLUX.1 Dev

FLUX.1 Krea Dev

FLUX.1 Schnell

FLUX.1.1 Pro

FLUX.1.1 Pro Ultra

FLUX.2 Dev

FLUX.2 Flex Edit

FLUX.2 Klein 4b

FLUX.2 Klein 9b

FLUX.2 Klein Base 4b

FLUX.2 Klein Base 9b