Luma Uni-1 Edit

POST/v1/run

Agent Uni 1 1.0 by Luma - 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 luma/agent/uni-1/1.0/edit.

Default: luma/agent/uni-1/1.0/edit

stringpromptrequired

Text prompt describing the edit to apply.

stringimagerequired

URL of the source image to edit.

Optional<string>output_format

Encoding format of the edited image.

Allowed values: png, jpeg

Optional<string>style

Visual style of the edited image.

Allowed values: auto, manga

Default: auto

Optional<array<string>>reference_image_urls

Optional list of reference image URLs used to guide the edit.

Response Schema

The submit endpoint returns a run response. If its status is pending or running, poll GET /v1/run/{id} with the returned opaque ID until it reaches a terminal state.

stringidrequired

Opaque SandBase run identifier. Use it exactly as returned; no prefix is guaranteed.

stringstatusrequired

Current public run status.

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

Optional<string>model

Public SandBase model name used for this run.

Optional<array<object>>outputs

Present only for completed runs. Each object is capability-specific; inspect the selected model schema for its fields.

Optional<object>error

Present only for failed or timeout runs. Contains a public error type and sanitized message.

Optional<string>error.type

Stable public error category.

Optional<string>error.message

Sanitized error message safe to show to clients.

Optional<object>usage

Usage details when available.

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": "luma/agent/uni-1/1.0/edit",
  "prompt": "Replace the background with a sunset over the ocean.",
  "image": "https://storage.googleapis.com/falserverless/gallery/example_inputs_liuyifei.png",
  "output_format": "png"
}'

# 2. If the response is still running, poll the returned id
curl https://api.sandbase.ai/v1/run/f3d2e8a1-7c4b-4a12-9d2e-123456789abc \
  -H "Authorization: Bearer $SANDBASE_API_KEY"

Response202 Accepted

{
  "id": "f3d2e8a1-7c4b-4a12-9d2e-123456789abc",
  "model": "luma/agent/uni-1/1.0/edit",
  "status": "running"
}