MiniMax H3 Max Lip Sync

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

execute_forge({
  "base_model_id": "minimax-h3-max-lip-sync",
  "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/minimax-h3-max-lip-sync/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "guidance_file_first_frame": [
          {
            "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"

seed

integer

The starting point for the model's randomness. The same seed and settings give the same result.

guidance_file_first_frame

file[]required

The frame the video starts on

guidance_file_reference_audio

file[]required

Guides style and voice without being modified