{
  "schema_version": 1,
  "id": "hyperflow-h3-flash-ref2va",
  "name": "HyperFlow H3 Flash Ref2VA",
  "size_multiple": 32,
  "description": "Generate video and audio with reference images. Use the HyperFlow H3 Flash Ref2VA transformer; video/audio references are not validated for these weights. Reuses MiniMax-H3 components with the HyperFlow 6-step schedule. Audio VAE is optional for silent video.",
  "model_url": "https://huggingface.co/VideoRebirthAI/hyperflow-h3-flash",
  "slots": [
    {
      "id": "diffusion_model",
      "required": true,
      "label": "HyperFlow H3 Flash REF2VA Transformer"
    },
    {
      "id": "llm",
      "required": true,
      "label": "MiniMax-H3 Qwen 3 VL 32B Text Encoder"
    },
    {
      "id": "vae",
      "required": false,
      "label": "MiniMax H3 Video VAE"
    },
    {
      "id": "tae",
      "required": false
    },
    {
      "id": "audio_vae",
      "required": false,
      "label": "MiniMax H3 Audio VAE"
    }
  ],
  "required_any": [
    [
      "vae",
      "tae"
    ]
  ],
  "video_constraints": {
    "frame_step": 17,
    "frame_offset": 5,
    "frame_rounding": "ceil",
    "min_frames": 5,
    "fixed_fps": 24
  },
  "defaults": {
    "video_frames": 124,
    "fps": 24,
    "cfg_scale": 1,
    "width": 1344,
    "height": 768,
    "sampling_method": "euler",
    "steps": 6,
    "flow_shift": 12,
    "custom_sigmas": [
      1.0,
      0.982655942,
      0.914642572,
      0.674755692,
      0.385223746,
      0.159055337,
      0.0
    ]
  },
  "features": [
    "flow_shift",
    "ref_images"
  ],
  "disabled_features": [
    "img2img",
    "mask_image"
  ]
}