Alibaba

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

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


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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
referenceImagesfile_arrayYes----Images to use as reference.
promptstringYes----Text instruction on how to edit the given image. If you are using a LoRA, use the LoRA instruction instead.
lorastringNo---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.
loraScalenumberNo104-Adjust the influence of the selected Qwen Edit LoRA
aspectRatiostringNomatch_input_image--match_input_image, 16:9, 4:3, 1:1, 3:4, 9:16Aspect ratio for the generated image
goFastbooleanNofalse---True runs the 8 steps Lightning preset
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
imagefileYes----Input image to edit.
promptstringNo----Optional text instruction appended after the camera directive.
rotateDegreesnumberNo0-9090-Camera orbit angle in degrees. Positive values move the camera to the left, while negative values move it to the right.
moveForwardnumberNo0010-Move the camera forward (zoom in). Higher values push towards a close-up.
verticalTiltnumberNo0-11-Vertical camera tilt. -1 = top-down, 1 = low-angle view.
useWideAnglebooleanNofalse---Switch to a wide-angle lens instruction.
aspectRatiostringNomatch_input_image--match_input_image, 16:9, 4:3, 1:1, 3:4, 9:16Aspect ratio for the generated image
loraScalenumberNo1.2504-Relative strength for the multi-angle LoRA.
goFastbooleanNofalse---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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
modelIdmodelNo----A single LoRA model ID. If provided, it will be added to the loras array.
lorasmodel_arrayNo``---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.
lorasScalenumber_arrayNo-02-Scales for the LoRA weights
promptstringYes----Text prompt for image editing
referenceImagesfile_arrayYes----Reference images for editing
numOutputsnumberNo114-Number of images to generate
numInferenceStepsnumberNo281100-The number of denoising steps
widthnumberNo-1282048-The width of the generated images, must be a multiple of 16
heightnumberNo-1282048-The height of the generated images, must be a multiple of 16
guidancenumberNo4110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
modelIdmodelNo----A single LoRA model ID. If provided, it will be added to the loras array.
lorasmodel_arrayNo``---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.
lorasScalenumber_arrayNo-02-Scales for the LoRA weights
promptstringYes----Text prompt for image editing
referenceImagesfile_arrayYes----Reference images for editing
numOutputsnumberNo114-Number of images to generate
numInferenceStepsnumberNo281100-The number of denoising steps
widthnumberNo-1282048-The width of the generated images, must be a multiple of 16
heightnumberNo-1282048-The height of the generated images, must be a multiple of 16
guidancenumberNo4110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
imagesfile_arrayYes----Input image to edit
horizontalAnglenumberNo00360-Horizontal angle (azimuth) in degrees: 0°=front, 90°=right side, 180°=back, 270°=left, 360°=front view again
verticalAnglenumberNo0-3090-Vertical angle (elevation) in degrees: -30°=low-angle, 0°=eye-level, 90°=bird's-eye
zoomnumberNo5010-Zoom - Distance level: 0=wide shot, 5=medium, 10=close-up
loraScalenumberNo1.504-LoRA scale controls camera control effect strength
numOutputsnumberNo114-Number of images to generate
numInferenceStepsnumberNo28150-Number of inference steps (higher = better quality, slower)
guidanceScalenumberNo4.5120-Guidance scale for generation (higher = closer to prompt)
accelerationstringNonone--none, regularAcceleration mode for faster generation
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
modelIdmodelNo----A single LoRA model ID. If provided, it will be added to the loras array.
lorasmodel_arrayNo``---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.
lorasScalenumber_arrayNo-02-Scales for the LoRA weights
promptstringYes----Text prompt for image editing
referenceImagesfileYes----Input image for editing
numOutputsnumberNo114-Number of images to generate
numInferenceStepsnumberNo281100-The number of denoising steps
widthnumberNo-1282048-The width of the generated images, must be a multiple of 16
heightnumberNo-1282048-The height of the generated images, must be a multiple of 16
guidancenumberNo4110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
modelIdmodelNo----A single LoRA model ID. If provided, it will be added to the loras array.
lorasmodel_arrayNo``---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.
lorasScalenumber_arrayNo-02-Scales for the LoRA weights
promptstringYes----Text prompt for image generation
imagefileNo----Input image for img2img
strengthnumberNo0.601-Lower values adhere more closely to the image, while higher values allow for more creative freedom
numOutputsnumberNo414-Number of images to generate
numInferenceStepsnumberNo281100-The number of steps for the generation
widthnumberNo-1282048-The width of the generated images, must be a multiple of 16
heightnumberNo-1282048-The height of the generated images, must be a multiple of 16
guidancenumberNo4110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
modelIdmodelNo----A single LoRA model ID. If provided, it will be added to the loras array.
lorasmodel_arrayNo``---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.
lorasScalenumber_arrayNo-02-Scales for the LoRA weights
promptstringYes----Text prompt for image generation
imagefileNo----Input image for img2img
strengthnumberNo0.601-Lower values adhere more closely to the image, while higher values allow for more creative freedom
numOutputsnumberNo414-Number of images to generate
numInferenceStepsnumberNo281100-Number of denoising steps. Use less steps for faster generation.
widthnumberNo-1282048-The width of the generated images, must be a multiple of 16
heightnumberNo-1282048-The height of the generated images, must be a multiple of 16
guidancenumberNo4110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
imagefileNo----Image to be converted into a layered image.
descriptionstringNoauto---Text description of the input image. Use 'auto' for auto captioning.
numLayersnumberNo428-Number of layers to generate.
goFastbooleanNotrue---Enable this option to run faster generations with additional optimizations (8 steps Lightning preset)
seednumberNo-02147483647-Use a seed for reproducible results. Leave blank to use a random seed.