Academia

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

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


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

ParameterTypeRequiredDefaultMinMaxAllowed ValuesDescription
imagefileYes----Input image to edit with physics-aware transformations.
promptstringYes----Editing instructions describing the physical transformation to apply.
negativePromptstringNo----Description of unwanted elements in the output.
numInferenceStepsnumberNo40150-Number of denoising steps.
cfgScalenumberNo4120-Classifier-free guidance scale.
seednumberNo-02147483647-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

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
negativePromptstringNo----Text prompt for what to avoid in the image
imagefileNo----Source image for img2img transformation
strengthnumberNo0.601-How much to transform the reference image. 0 means no change, 1 means complete transformation
controlImagefile_arrayNo----Control images to use as input (edge, depth, or pose)
controlnetConditioningScalenumberNo0.7501-The scale of the controlnet conditioning
numOutputsnumberNo414-Number of images to generate
numInferenceStepsnumberNo281100-Number of inference 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
guidancenumberNo5110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-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

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
negativePromptstringNo----Text prompt for what to avoid in the image
imagefileNo----Source image for img2img transformation. Cannot be used with ControlNet.
strengthnumberNo0.7501-How much to transform the reference image. 0 means no change, 1 means complete transformation
controlImagefile_arrayNo----Control images to use as input (edge, depth, or pose). Cannot be used with Reference Image.
controlnetConditioningScalenumberNo0.701-The scale of the controlnet conditioning
numOutputsnumberNo414-Number of images to generate
numInferenceStepsnumberNo91100-Number of inference steps.
widthnumberNo-1282048-Width of the generated image
heightnumberNo-1282048-Height of the generated image
seednumberNo-02147483647-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

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
negativePromptstringNo----Text prompt for what to avoid in the image
controlImagefile_arrayYes----Control images to use as input (edge, depth, or pose)
controlnetConditioningScalenumberNo0.7501-The scale of the controlnet conditioning
numOutputsnumberNo114-Number of images to generate
numInferenceStepsnumberNo91100-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
guidancenumberNo1110-Controls how closely the generated image follows the prompt
seednumberNo-02147483647-Used to reproduce previous results