Model Create

Model Create enables you to generate realistic fashion models with simple, intuitive prompts or reference images.

Model Specifications

Model Name: model-create
Lifecycle: experimental
Processing Time: 20s–120s (see below)
Output Formats: PNG, JPEG
Delivery Methods: URL or Base64 encoding
Credits: 1-5 per output image depending on resolution and generation_mode (+3 per output image with face_reference)

Request

Generate fashion models by submitting your prompt and optional reference assets 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-create",
           "inputs": {
             "prompt": "Full body shot, woman wearing a white t-shirt and dark blue biker shorts"
           }
         }'

Response

Returns a prediction ID for status polling:

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

Request Parameters

Required Parameters

`prompt`
Required
string

Prompt for the model image generation. Describes the desired fashion model, clothing, pose, and scene.

Optional Parameters

`image_reference`image URL | base64

Optional image to guide composition and pose. The AI won't copy the exact details from the image, but will use it as inspiration.

You can control whether to copy just the pose or the exact silhouette using the prompt parameter with natural language.

Base64 Format

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

`aspect_ratio`string

Defines the width-to-height ratio of the generated image.

When image_reference is provided, the output inherits the reference image's aspect ratio. Supply an explicit aspect_ratio to override that default.

Supported ratios: "21:9", "16:9", "9:16", "4:3", "3:4", "3:2", "2:3", "4:5", "5:4", "1:1".

Default: 1:1

`face_reference`image URL | base64

Optional portrait image that locks in a specific identity across generations.

When face_reference is used, output resolution is capped at 2K regardless of the requested resolution tier.
Adds 3 credits per image.
Adds roughly 20-30 seconds of processing time.

Use this to achieve model consistency across generations without training a custom checkpoint.

`face_reference_mode`'match_base' | 'match_reference'

Controls how the provided face_reference shapes pose and expression.

-match_base prioritizes the prompt and base generation, keeping the original pose while adapting the reference face to those instructions.

-match_reference aligns the generated model closely with the reference face’s pose, gaze, and expression for maximum resemblance.

Default: match_reference

`resolution`'1k' | '2k' | '4k'

Output resolution tier. '1k' produces ~1 megapixel output, '2k' ~4 megapixels, and '4k' ~16 megapixels. Exact output dimensions depend on this tier and the image aspect ratio.

Default: '1k'

`generation_mode`'fast' | 'balanced' | 'quality'

Sets the generation quality level. 'quality' produces the most detailed and realistic output but takes longer to process and costs more credits. 'fast' prioritizes speed and lower cost. If omitted, FASHN selects generation_mode automatically. For model-create, omitted generation_mode is currently billed as 'fast' at 1k and as 'quality' at 2k or 4k.

`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

`num_images`integer

Number of images to generate per request. Must be between 1 and 4. Additional images consume more compute (and credits) and can increase processing time.

Default: 1

`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 returns the generated image as a base64 string instead of a CDN URL. The base64 output is prefixed according to output_format (e.g., data:image/png;base64,... or data:image/jpeg;base64,...).

Enables stricter privacy because images are never uploaded to our CDN and are only available for 60 minutes after completion.

Default: false

Credit Cost

`generation_mode` \ `resolution`	`1k`	`2k`	`4k`
`fast`	1	2	3
`balanced`	2	3	4
`quality`	3	4	5

Additional pricing rules:

face_reference adds +3 credits per output image.
num_images multiplies the total cost by the number of outputs requested.
If generation_mode is omitted, automatic pricing applies.

Processing Time

Processing time depends on both resolution and generation_mode. The fastest configuration (fast + 1k) typically completes in under 20 seconds, while the most intensive (quality + 4k) can take up to 120 seconds. Actual latency may vary with current server load.

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 creation 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 generated fashion model images based on your prompt and optional reference parameters.

Runtime Errors

Runtime errors for Model Create use the shared set in Error Handling.

For detailed implementation guidance and best practices:

Image Preprocessing Best Practices - Optimize your reference images

Model Create

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

Response

promptRequiredstring

image_referenceimage URL | base64

aspect_ratiostring

face_referenceimage URL | base64

face_reference_mode'match_base' | 'match_reference'

resolution'1k' | '2k' | '4k'

generation_mode'fast' | 'balanced' | 'quality'

seedinteger

num_imagesinteger

output_format'png' | 'jpeg'

return_base64boolean

On this page