{
    "model": {
        "name": "LongCat Avatar 1.5 Distilled 13.6B",
        "architecture": "longcat_avatar_v1_5",
        "description": "LongCat Avatar 1.5 distilled audio-driven avatar video generation.",
        "URLs": [
            "https://huggingface.co/DeepBeepMeep/LongCat/resolve/main/longcat_avatar_v1_5_bf16.safetensors",
            "https://huggingface.co/DeepBeepMeep/LongCat/resolve/main/longcat_avatar_v1_5_quanto_bf16_int8.safetensors"
        ],
        "reference_image_enabled": true,
        "ref_img_index": 10,
        "mask_frame_range": 3,
        "sample_solver": "distill"
    },
    "prompt": "A person speaking naturally with expressive eye contact and accurate lip sync.",
    "negative_prompt": "Close-up, overexposed, static, blurred details, distorted mouth, extra teeth.",
    "num_inference_steps": 8,
    "guidance_scale": 1.0,
    "audio_guidance_scale": 1.0,
    "video_length": 93,
    "sample_solver": "distill"
}