FLUX Virtual Try-On

POST/v1/run

Flux Pro 1.0 Vto by BFL - AI-powered image editing, style transfer, and transformation. Edit photos with natural language instructions, remove backgrounds, change styles, and enhance images effortlessly.

Request body

Submit an async generation request. The model field selects the model; other fields are model-specific input parameters.

stringmodelrequired

Model identifier. Set to bfl/flux-pro/1.0/vto.

Default: bfl/flux-pro/1.0/vto

stringpromptrequired

Natural-language styling instructions describing how the garment should be worn on the person (e.g. tucked in, layered, sleeves rolled up).

Optional<integer>num_inference_steps

The number of denoising steps to perform.

Range: 1 to 4

Default: 4

Optional<string>output_format

The format of the generated image.

Allowed values: jpeg, png

Default: jpeg

Optional<integer>seed

The same seed and the same input will output the same image every time. If not provided, a random seed is used.

Optional<string>garment_image_url

The URL of the garment reference image. Maximum 1 megapixel; recommended around 0.5 MP. Multiple garments must be merged into a single composite image before submission.

Optional<string>human_image_url

The URL of the person image that the garment will be applied onto. The output keeps this image's aspect ratio. Maximum 2 megapixels; recommended under 1 MP.

Response Schema

The submit endpoint returns an accepted generation task. Poll the result endpoint with the returned id for terminal outputs or errors.

Optional<string>error

Error message if the task failed. Empty on success.

stringidrequired

Unique identifier for the generation task.

Optional<string>model

Model ID used for the prediction.

Optional<array>outputs

Array of generated content. Empty when status is not completed.

stringstatusrequired

Status of the task: pending, running, completed, failed, or timeout.

Allowed values: pending, running, completed, failed, timeout

Model capabilities

array<string>capability_tagsrequired

Capabilities declared by the model registry.

Default: image-to-image

stringexecution_moderequired

Execution mode declared by the model registry.

Default: async

# 1. Submit a generation request
curl -X POST https://api.sandbase.ai/v1/run \
  -H "Authorization: Bearer $SANDBASE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "bfl/flux-pro/1.0/vto",
  "prompt": "A natural front-facing studio shot. The t-shirt is worn tucked in.",
  "output_format": "jpeg"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/run_abc123 \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "run_abc123",
  "model": "bfl/flux-pro/1.0/vto",
  "status": "running",
  "outputs": []
}