Topaz Artemis High Quality

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

execute_forge({
  "base_model_id": "topaz-artemis-high-quality-upscale-video",
  "prompt": "A torch-lit dungeon corridor, slow dolly forward",
  "batch_size": 1
})

# 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-artemis-high-quality-upscale-video/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "guidance_file_init_video": [
          {
            "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 21, 2, 4

How many times larger the output is than the source.

recover_detail

number0–1

How much of the source's own detail is recovered and kept.

denoise

number0–1

Removes noise and grain from the source.

compression_repair

number0–1

Removes blocking and ringing left by JPEG or video compression.

halo_reduction

number0–1

Removes bright outlines along edges from an oversharpened source.

grain

number0–0.1

Film grain laid back over the cleaned result.

target_fps

integerdefault 3016–60

Frames generated in between the source's own. Resolution is unchanged.

guidance_file_init_video

file[]required

The video to modify