HunyuanCustom MCP: subject-consistent video with no API key

From an agent, through the MCP

The agent calls get_model_schema, then run_model with:

{
  "endpoint_id": "flymyai/hunyuan-custom",
  "input": {
    "prompt": "Slow camera push-in with gentle, natural motion in the scene",
    "negative_prompt": "Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border.",
    "width": "512",
    "height": "896",
    "num_frames": "129",
    "num_inference_steps": "30"
  }
}

From your code, over HTTP

Form fields, not JSON; files go as uploads or public URLs. The answer is a prediction_id; read the result at https://api.flymy.ai/api/v1/flymyai/hunyuan-custom/predict/async/result/?request_id=<prediction_id>.

curl -X POST https://api.flymy.ai/api/v1/flymyai/hunyuan-custom/predict/async/ \
  -H "X-API-KEY: $FLYMYAI_API_KEY" \
  -F 'prompt=Slow camera push-in with gentle, natural motion in the scene' \
  -F 'negative_prompt=Aerial view, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border.' \
  -F 'width=512' \
  -F 'height=896' \
  -F 'num_frames=129' \
  -F 'num_inference_steps=30'