mirror of
https://github.com/Wan-Video/Wan2.1.git
synced 2025-11-04 06:15:17 +00:00
38 lines
1.6 KiB
JSON
38 lines
1.6 KiB
JSON
{
|
|
"model": {
|
|
"name": "Wan2.1 Text2video Self-Forcing 14B",
|
|
"architecture": "t2v",
|
|
"description": "This model is an advanced text-to-video generation model. This approach 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
|
|
},
|
|
"negative_prompt": "",
|
|
"prompt": "",
|
|
"resolution": "832x480",
|
|
"video_length": 81,
|
|
"seed": -1,
|
|
"num_inference_steps": 4,
|
|
"guidance_scale": 1,
|
|
"flow_shift": 3,
|
|
"embedded_guidance_scale": 6,
|
|
"repeat_generation": 1,
|
|
"multi_images_gen_type": 0,
|
|
"tea_cache_setting": 0,
|
|
"tea_cache_start_step_perc": 0,
|
|
"loras_multipliers": "",
|
|
"temporal_upsampling": "",
|
|
"spatial_upsampling": "",
|
|
"RIFLEx_setting": 0,
|
|
"slg_switch": 0,
|
|
"slg_start_perc": 10,
|
|
"slg_end_perc": 90,
|
|
"cfg_star_switch": 0,
|
|
"cfg_zero_step": -1,
|
|
"prompt_enhancer": "",
|
|
"activated_loras": []
|
|
} |