Image Upscale Models - Parameters Reference

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

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

Models

Scenario

Scenario Gemini Upscale

Model ID: model_scenario-gemini-upscale

Capabilities: img2img

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Input image to upscale
`prompt`	string	No	-	-	-	-	User prompt for image upscaling
`upscaleFactor`	string	No	`4k`	-	-	`4k`	Target resolution
`creativity`	number	No	`50`	0	100	-	Creativity level from 0 to 100
`seed`	number	No	-	0	-	-	Seed for generation

Scenario Upscale V3

Model ID: model_upscale-v3

Capabilities: img2img

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to upscale
`style`	string	No	`standard`	-	-	`standard`, `cartoon`, `anime`, `comic`, `minimalist`, `photography`, `3d-rendered`	Selecting a custom style will optimize settings for the output image to match the selected style
`upscaleFactor`	number	No	`2`	1	16	-	Scaling factor (when target width not specified). If 1, then it's a refinement step only
`preset`	string	No	`precise`	-	-	`precise`, `balanced`, `creative`	Select a preset to apply a set of parameters
`styleImages`	file_array	No	-	-	-	-	Upload up to 10 images for the AI to learn from and shape the style of your final output
`styleStrength`	number	No	`0.5`	0	3	-	Higher fidelity keeps the enhanced image's style closely aligned with the style images.
`tileStyle`	boolean	No	`false`	-	-	-	If set to true, during the upscaling process, the model will match tiles of the source image with tiles of the style image. This will result in a more coherent style transfer. Works best with style images that have a similar composition.
`prompt`	string	No	-	-	-	-	Prompt
`negativePrompt`	string	No	-	-	-	-	-
`guidanceScale`	number	No	`6`	0	10	-	Higher fidelity prioritizes the prompt over the image
`controlnetConditioningScale`	number	No	`0.8`	0	1.2	-	Higher fidelity keeps the enhanced image closer to the original structure of the input image
`strength`	number	No	`0.1`	0.1	1	-	Higher creativity levels introduce extra imaginative elements to enhanced images
`fractality`	number	No	`0`	0	1	-	Fractality will add small fractal-like details, possibly repeating intricated patterns and repeating these details across tiles
`loraDetailsScale`	number	No	`0`	-1.5	1.5	-	Enhances or reduces the intensity of the details
`seed`	number	No	-	0	2147483647	-	Seed used for reproduction
`strengthDecay`	number	No	`0.8`	0.1	1	-	The degree of creativity retained at each stage of the enhancement process (only applies for scale factors above 2)
`overrideEmbeddings`	boolean	No	`false`	-	-	-	Removes any additional custom embeddings used to guide the 'Style'

Academia

Pixel Snapper

Model ID: model_pixel-snapper

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_pixel-snapper/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to process
`colors`	number	No	`16`	8	256	-	Number of colors to use in the color quantization
`seed`	number	No	-	0	2147483647	-	Seed for reproducibility

BFL

Scenario Flux Upscale

Model ID: model_sc-upscale-flux

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_sc-upscale-flux/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, FLUX.1-Krea-dev for realistic images
`seed`	number	No	-	0	2147483647	-	Seed used for reproduction

Bytedance

SeedVR2 - Image Upscale

SeedVR2 Upscale Image is a model that can upscale images.

Model ID: model_seedvr-2-upscale-image

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_seedvr-2-upscale-image/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`imageUrl`	file	Yes	-	-	-	-	Image to upscale
`upscaleMode`	string	No	`factor`	-	-	`factor`, `target`	The mode to use for the upscale. If 'target', the upscale factor will be calculated based on the target resolution. If 'factor', the upscale factor will be used directly.
`upscaleFactor`	number	No	`2`	2	10	-	How much to upscale the image
`targetResolution`	string	No	`1080p`	-	-	`720p`, `1080p`, `1440p`, `2160p`	The target resolution to upscale to when Upscale Mode is target.
`noiseScale`	number	No	`0.1`	0	1	-	The noise scale to use for the generation process.
`seed`	number	No	-	-	-	-	Random seed for reproducibility. If None, a random seed is chosen.

Clarity AI

Crystal Upscaler

High-precision image upscaler optimized for portraits and faces.

Model ID: model_crystal-upscaler

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_crystal-upscaler/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	An input image for upscaling
`scaleFactor`	number	No	`2`	1	200	-	Scale factor for upscaling. It will be automatically adjusted to fit within memory limits
`creativity`	number	No	`0`	0	10	-	Creativity level for upscaling

Magnific

Magnific Upscaler Creative

Model ID: model_magnific-upscaler-creative

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_magnific-upscaler-creative/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	The image to upscale.
`prompt`	string	No	-	-	-	-	The prompt to upscale the image.
`scaleFactor`	string	No	`2x`	-	-	`2x`, `4x`, `8x`, `16x`	The scale factor of the upscaler.
`optimizedFor`	string	No	`standard`	-	-	`standard`, `soft_portraits`, `hard_portraits`, `art_n_illustration`, `videogame_assets`, `nature_n_landscapes`, `films_n_photography`, `3d_renders`, `science_fiction_n_horror`	The optimized for of the upscaler.
`creativity`	number	No	`0`	-10	10	-	The creativity of the upscaler.
`hdr`	number	No	`0`	-10	10	-	The HDR of the upscaler.
`resemblance`	number	No	`0`	-10	10	-	The resemblance of the upscaler.
`fractality`	number	No	`0`	-10	10	-	The fractality of the upscaler.
`engine`	string	No	`automatic`	-	-	`automatic`, `magnific_illusio`, `magnific_sharpy`, `magnific_sparkle`	The engine of the upscaler.

Magnific Upscaler Precision

Model ID: model_magnific-upscaler-precision

Capabilities: img2img

LLM Markdown: https://app.scenario.com/api/models/model_magnific-upscaler-precision/markdown

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	The image to upscale.
`sharpen`	number	No	`7`	0	100	-	Whether to sharpen the image.
`smartGrain`	number	No	`7`	0	100	-	Whether to use smart grain.
`ultraDetail`	number	No	`30`	0	100	-	Whether to use ultra detail.
`flavor`	string	No	`sublime`	-	-	`sublime`, `photo`, `photo_denoiser`	The flavor of the upscaler.
`scaleFactor`	number	No	`2`	2	16	-	The scale factor of the upscaler.

Recraft AI

Recraft Creative Upscale

Recraft Creative upscales image with a creative style.

Model ID: model_recraft-creative-upscale

Capabilities: img2img

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to upscale

Recraft Crisp Upscale

Recraft Crisp Upscale increases overall quality, making visuals suitable for web use or print-ready materials

Model ID: model_recraft-crisp-upscale

Capabilities: img2img

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to upscale

Topaz Labs

Topaz Image Upscale

Model ID: model_topaz-image-upscale

Capabilities: img2img

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

Parameter	Type	Required	Default	Min	Max	Allowed Values	Description
`image`	file	Yes	-	-	-	-	Image to enhance
`enhanceModel`	string	No	`Standard V2`	-	-	`Standard V2`, `Low Resolution V2`, `CGI`, `High Fidelity V2`, `Text Refine`	Model to use: Standard V2 (general purpose), Low Resolution V2 (for low-res images), CGI (for digital art), High Fidelity V2 (preserves details), Text Refine (optimized for text)
`upscaleFactor`	string	No	`2x`	-	-	`None`, `2x`, `4x`, `6x`	How much to upscale the image
`subjectDetection`	string	No	`None`	-	-	`None`, `All`, `Foreground`, `Background`	Subject detection
`faceEnhancement`	boolean	No	`false`	-	-	-	Enhance faces in the image
`faceEnhancementCreativity`	number	No	`0`	0	1	-	Choose the level of creativity for face enhancement from 0 to 1. Defaults to 0, and is ignored if face_enhancement is false.
`faceEnhancementStrength`	number	No	`0.8`	0	1	-	Control how sharp the enhanced faces are relative to the background from 0 to 1. Defaults to 0.8, and is ignored if face_enhancement is false.