Model Variation

Model Variation enables you to create new variations of existing fashion model images. Transform your images with subtle adjustments or strong modifications while maintaining the core composition.

Model Specifications

Model Name: model-variation
Processing Time: 8-10 seconds
Supported Resolution: up to 1.05MP

Request

Create variations of existing fashion model images by submitting the source image to the universal /v1/run endpoint:

POST`https://api.fashn.ai/v1/run`

Request Examples

curl -X POST https://api.fashn.ai/v1/run \
     -H "Content-Type: application/json" \
     -H "Authorization: Bearer YOUR_API_KEY" \
     -d '{
           "model_name": "model-variation",
           "inputs": {
             "model_image": "https://example.com/fashion-model.jpg",
             "variation_strength": "subtle"
           }
         }'

Response

Returns a prediction ID for status polling:

{
  "id": "123a87r9-4129-4bb3-be18-9c9fb5bd7fc1-u1",
  "error": null
}

Request Parameters

Required Parameters

`model_image`
Required
image URL | base64

Source fashion model image to create variations from. The variation will maintain the core composition while introducing controlled modifications.

Base64 Format

Base64 images must include the proper prefix (e.g., data:image/jpg;base64,<YOUR_BASE64>)

Optional Parameters

`variation_strength`'subtle' | 'strong'

Controls the intensity of variations applied to the source image.

subtle – Minor adjustments that preserve most of the original characteristics while introducing small variations
strong – More significant modifications that create noticeable differences while maintaining the core composition

Default: subtle

`seed`integer

Sets random operations to a fixed state. Use the same seed to reproduce results with the same inputs, or different seed to force different results.

Default: 42
Range: 0 to 2^32 - 1

`lora_url`file URL

URL to a FLUX-based LoRA weights file (.safetensors) for custom identity generation. When provided, the LoRA will be loaded and applied during generation to maintain consistent character appearance across generations.

LoRA Requirements

Architecture: Must be FLUX-compatible LoRA weights
Format: .safetensors file format only
File Size: Must be under 256MB

Example: https://example.com/custom_identity.safetensors

`output_format`'png' | 'jpeg'

Specifies the desired output image format.

-png: Delivers the highest quality image, ideal for use cases such as content creation where quality is paramount.
-jpeg: Provides a faster response with a slightly compressed image, more suitable for real-time applications.

Default: png

`return_base64`boolean

When set to true, the API will return the generated image as a base64-encoded string instead of a CDN URL. The base64 string will be prefixed according to the output_format (e.g., data:image/png;base64,... or data:image/jpeg;base64,...).

This option offers enhanced privacy as user-generated outputs are not stored on our servers when return_base64 is enabled.

Default: false

Response Polling

After submitting your request, poll the status endpoint using the returned prediction ID. See API Fundamentals for complete polling details.

Successful Response

When your model variation completes successfully, the status endpoint will return:

{
  "id": "123a87r9-4129-4bb3-be18-9c9fb5bd7fc1-u1",
  "status": "completed",
  "output": [
    "https://cdn.fashn.ai/123a87r9-4129-4bb3-be18-9c9fb5bd7fc1-u1/output_0.png"
  ],
  "error": null
}

The output array contains URLs to your variation images with controlled modifications applied to the original composition.

Runtime Errors

Model Variation may encounter the following model-specific errors during processing:

Name Cause Solution

Name	Cause	Solution
`ImageLoadError`	The pipeline was unable to load the model image from the provided inputs.	For Image URLs: Ensure the URL is publicly accessible and not restricted by permissions. Verify that the Content-Type header specifies the correct image format (e.g., image/jpeg, image/png). For Base64-encoded images: Prefix the string with data:image/`format`;base64, where format is the image type (e.g., jpeg, png).
`LoRALoadError`	Failed to download or load the LoRA weights file from the provided URL.	Ensure the LoRA URL is publicly accessible and returns a valid .safetensors file. Check that the file size is under 256MB. Ensure the LoRA is compatible with the FLUX.1-dev model.
`PipelineError`	An unexpected error occurred during the execution of the pipeline.	Retry the request (you will not be charged for failed attempts). If the issue persists, please reach out to us at support@fashn.ai and include the prediction ID from the failed attempt to help us locate and address the issue promptly.

ImageLoadError

The pipeline was unable to load the model image from the provided inputs.

For Image URLs:

Ensure the URL is publicly accessible and not restricted by permissions.
Verify that the Content-Type header specifies the correct image format (e.g., image/jpeg, image/png).

For Base64-encoded images:

Prefix the string with data:image/format;base64, where format is the image type (e.g., jpeg, png).

LoRALoadError

Failed to download or load the LoRA weights file from the provided URL.

Ensure the LoRA URL is publicly accessible and returns a valid .safetensors file.
Check that the file size is under 256MB.
Ensure the LoRA is compatible with the FLUX.1-dev model.

PipelineError An unexpected error occurred during the execution of the pipeline. Retry the request (you will not be charged for failed attempts). If the issue persists, please reach out to us at support@fashn.ai and include the prediction ID from the failed attempt to help us locate and address the issue promptly.

The Error Object

{
  "error": {
    "name": "PipelineError",
    "message": "The error message"
  }
}

Example of an error when polling the /status endpoint:

{
  "id": "123a87r9-4129-4bb3-be18-9c9fb5bd7fc1-u1",
  "status": "failed",
  "error": {
    "name": "ImageLoadError",
    "message": "Error loading model image: The URL's Content-Type is not an image. Content-Type: text/plain;charset=UTF-8"
  }
}

If you encounter an unrecognized error, please contact us at support@fashn.ai.

For detailed implementation guidance and best practices:

Image Preprocessing Best Practices - Optimize your source images for variation generation

Model Variation

POSThttps://api.fashn.ai/v1/run

Response

model_imageRequiredimage URL | base64

variation_strength'subtle' | 'strong'

seedinteger

lora_urlfile URL

output_format'png' | 'jpeg'

return_base64boolean