{
    "model": {
        "name": "Wan2.1 Text2video Lightning 14B",
        "architecture": "t2v",
        "description": "This model is an advanced text-to-video generation model. The Lightning / SelfForcing process allows the model to generate videos with significantly fewer inference steps (4 or 8 steps) and without classifier-free guidance, substantially reducing video generation time while maintaining high quality outputs.",
        "URLs": [
            "https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_bf16.safetensors",
            "https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_bf16_int8.safetensors",
            "https://huggingface.co/DeepBeepMeep/Wan2.1/resolve/main/wan2.1_StepDistill-CfgDistill_14B_quanto_fp16_int8.safetensors"
        ],
		"author": "https://huggingface.co/lightx2v/Wan2.1-T2V-14B-StepDistill-CfgDistill",
        "auto_quantize": true
    },
    "num_inference_steps": 4,
    "guidance_scale": 1,
    "flow_shift": 3
}