Flux Vision Upscaler

POST/v1/run

Flux Vision Upscaler 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-vision-upscaler.

Default: bfl/flux-vision-upscaler

stringimagerequired

The URL of the image to upscale.

Optional<number>upscale_factor

The upscale factor (1-4x).

Range: 1 to 4

Default: 2

Optional<integer>steps

Number of inference steps (4-50).

Range: 4 to 50

Default: 20

Optional<number>creativity

The creativity of the model. The higher the creativity, the more the model will deviate from the original. Refers to the denoise strength of the sampling.

Range: 0 to 1

Default: 0.3

Optional<number>guidance

CFG/guidance scale (1-4). Controls how closely the model follows the prompt.

Range: 1 to 4

Default: 1

Optional<integer>seed

The seed to use for the upscale. If not provided, a random seed will be used.

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-vision-upscaler",
  "image": "https://static.sandbase.ai/examples/bfl/flux-vision-upscaler/input_image_0.jpg"
}'

# 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-vision-upscaler",
  "status": "running",
  "outputs": []
}