FASHN modelsimage generation api

fashn/tryon/v1.6

Name: FASHN Virtual Try-On V1.6
Author: FASHN

Tryon V1.6 by FASHN - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Input

Output Format(string)

Output format of the generated images. 'png' is highest quality, while 'jpeg' is faster Allowed values: png, jpeg.

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.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL or base64 of the model image

Garment Photo Type(string)

Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type. Allowed values: auto, model, flat-lay.

Segmentation Free(boolean)

Disables human parsing on the model image.

Image URL or upload(string)

Upload

PNG, JPEG, WebP, or GIF · 20 MiB maximum

URL or base64 of the garment image

Category(string)

Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment. Allowed values: tops, bottoms, one-pieces, auto.

Moderation Level(string)

Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear. Allowed values: none, permissive, conservative.

Num Samples(integer)

Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result. Range: 1 to 4.

Idle

Example output — click Run to generate your own

Production endpoint

Send your first request

OpenAI-compatible endpoint with unified authentication and usage tracking.

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

Model IDfashn/tryon/v1.6

Input Schema

9 parameters · 0 required · 9 optional

Parameter	Type	Required	Description
`seed`	integer	Optional	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.
`category`	string	Optional	Category of the garment to try-on. 'auto' will attempt to automatically detect the category of the garment. · Options: tops, bottoms, one-pieces, auto · Default: "auto" topsbottomsone-piecesauto
`model_image`	string	Optional	URL or base64 of the model image
`num_samples`	integer	Optional	Number of images to generate in a single run. Image generation has a random element in it, so trying multiple images at once increases the chances of getting a good result. · Min: 1 · Max: 4 · Default: 1
`garment_image`	string	Optional	URL or base64 of the garment image
`output_format`	string	Optional	Output format of the generated images. 'png' is highest quality, while 'jpeg' is faster · Options: png, jpeg · Default: "png" pngjpeg
`moderation_level`	string	Optional	Content moderation level for garment images. 'none' disables moderation, 'permissive' blocks only explicit content, 'conservative' also blocks underwear and swimwear. · Options: none, permissive, conservative · Default: "permissive" nonepermissiveconservative
`segmentation_free`	boolean	Optional	Disables human parsing on the model image. · Default: true
`garment_photo_type`	string	Optional	Specifies the type of garment photo to optimize internal parameters for better performance. 'model' is for photos of garments on a model, 'flat-lay' is for flat-lay or ghost mannequin images, and 'auto' attempts to automatically detect the photo type. · Options: auto, model, flat-lay · Default: "auto" automodelflat-lay

Output Schema

Field	Type	Description
`id`	string	Unique identifier for the generation task
`status`	string	Task status: pending, running, completed, failed, timeout
`model`	string	Model used for the generation
`outputs`	array	Array of output items
`outputs[].url`	string	URL of the generated artifact
`outputs[].content_type`	string	MIME type (e.g. image/png, video/mp4)
`error`	object \| null	Error details if failed, null on success
`error.type`	string	Machine-readable error type code
`error.message`	string	Human-readable error description

Async Workflow

This model uses asynchronous execution. Submit a request and poll for the result.

Submit — POST to /v1/run, receive an id
Poll — GET /v1/run/{id} until status is completed, failed, or timeout
Retrieve — Read outputs from the completed response

Code Examples

Ready-to-run snippets

# Step 1: Submit
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
  "model": "fashn/tryon/v1.6",
  "category": "auto",
  "model_image": "https://static.sandbase.ai/examples/fashn/tryon/v1.6/input_model_image_0.png",
  "num_samples": 1,
  "garment_image": "https://static.sandbase.ai/examples/fashn/tryon/v1.6/input_garment_image_1.webp",
  "output_format": "png",
  "moderation_level": "permissive",
  "segmentation_free": true,
  "garment_photo_type": "auto",
  "prompt": "a beautiful sunset over mountains"
}'

# Step 2: Poll result (replace <id>)
curl https://api.sandbase.ai/v1/run/<id> \
  -H "Authorization: Bearer YOUR_API_KEY"

← Back to FASHN Virtual Try-On V1.6

API README

FASHN Virtual Try-On V1.6

fashn/tryon/v1.6 produces high-fidelity virtual try-on imagery by transferring a garment onto a person while retaining identity, body proportions, pose, and scene context. Version 1.6 improves garment-detail preservation and robustness across both flat-lay and on-model clothing references, helping logos, patterns, seams, and distinctive construction survive the transfer. This combination makes the model a practical choice when the creative outcome depends on those qualities rather than on a generic media conversion.

For production work, It is suited to customer previews, catalog expansion, and creative merchandising where the final image must look naturally worn while staying faithful to the photographed product. The result is most reliable when the source material and creative brief clearly describe the intended subject, progression, visual or sonic character, and the qualities that must remain unchanged.

Highlights

Improved garment fidelity preserves logos, patterns, seams, and construction details.

Robust reference handling works with flat-lay products as well as on-model garments.

Person and pose preservation maintain the target subject's identity and body structure.

Natural fit synthesis adapts drape, occlusion, and garment placement to the wearer.

Pricing

Billing unit	Price
Per request	$0.075

When to Use

✅ Good fit	❌ Consider alternatives
The model's named workflow matches the source material and intended output	A different input modality or model route is required
A managed asynchronous result is suitable for the production pipeline	A synchronous, interactive editor is essential
The documented controls cover the required duration, framing, or format	The project needs controls outside this endpoint's schema
Creative iteration benefits from a repeatable request structure	Exact deterministic pixels, frames, geometry, or samples are mandatory
A finished downloadable media asset is the desired deliverable	Editable source layers or a native project file are required

Prompt Guide

For generation, state the intended result first, then add the subject or source treatment, progression, style, and delivery constraints. Keep one creative variable per phrase, use the documented field names for controls, and change one setting at a time when comparing results.

{
  "output_format": "png"
}

Technical Specs

Spec	Value
Model ID	`fashn/tryon/v1.6`
Inputs	category, garment_image, garment_photo_type, model_image, moderation_level, num_samples, output_format, seed, segmentation_free
Required inputs	None
Output fields	content_type, url
Execution	Async (submit, then poll for result)
Output Format	png / jpeg