Topaz CGI

https://mcp.app.layer.ai/mcp

execute_forge({
  "base_model_id": "topaz-cgi-upscale-image",
  "prompt": "A crystal sword icon on a transparent background, game UI art",
  "batch_size": 4,
  "width": 1024,
  "height": 1024
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/topaz-cgi-upscale-image/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "guidance_file_init_image": [
          {
            "url": "https://example.com/input.png"
          }
        ]
      }'

# Poll until status is "complete" — the response then carries the asset URLs.
curl https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/inferences/$INFERENCE_ID \
  -H "Authorization: Bearer $LAYER_TOKEN"

upscale_factor

enumdefault 22, 4

How many times larger the output is than the source.

target_region

enumdefault ALLALL, SUBJECT, BACKGROUND

The part of the image the model works on.

face_enhancement

booleandefault true

Restore faces in a separate pass.

face_enhancement_strength

number0–1

How strongly faces are restored. Applies with face enhancement on.

face_enhancement_creativity

number0–1

How much new facial detail is invented. Applies with face enhancement on.

denoise

number0–1

Removes noise and grain from the source.

sharpness

number0–1

How much the result is sharpened.

guidance_file_init_image

file[]required

The image to modify

output_fit

any

Trim the transparent margin, and place the image on a canvas of a fixed size.