Wan 2.1

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

execute_forge({
  "base_model_id": "wan-21",
  "prompt": "A torch-lit dungeon corridor, slow dolly forward",
  "batch_size": 1,
  "duration_seconds": 5
})

# Start the generation — returns an inference id straight away.
curl -X POST https://api.app.layer.ai/api/v2/workspaces/$WORKSPACE_ID/base-models/alibaba-wan-2-1/inferences \
  -H "Authorization: Bearer $LAYER_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
        "prompt": "A torch-lit dungeon corridor, slow dolly forward"
      }'

# 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"

prompt

string

Describe what to generate, or the change to make.

negative_prompt

string

What to keep out of the result.

aspect_ratio

enumdefault LANDSCAPE_16_9_720p4 options

The shape and size of the output.

quality

enumdefault HIGHMEDIUM, HIGH

Higher levels render more detail, and can take longer and cost more.

prompt_enhancement

enumdefault AUTOAUTO, OFF, STANDARD

Let the model rewrite the prompt before generating.

seed

integer

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

inference_steps

integerdefault 302–40

How many refinement passes the model makes. More add detail and take longer.

duration_seconds

integerdefault 5

Length of the generated clip, in seconds.

guidance_file_first_frame

file[]

The frame the video starts on

guidance_file_last_frame

file[]

The frame the video ends on

prompt_language

string

The language the prompt is written in, so it reaches the model as you meant it.