Wan2.1-T2V-1.3B-Self-Forcing-DMD-FP8
0 0 1

其他

V1.0

The process involved extracting VACE scopes and injecting into the target models.

FP16 model weight was then quantized to specific FP8 formats (E4M3FN and E5M2) using ComfyUI custom node ComfyUI-ModelQuantizer by lum3on.

The model files can be used in ComfyUI with the WanVaceToVideo node. Place the required model(s) in the following folders:

Type	Name	Location	Download
Main Model	Wan2.1-T2V-1.3B-Self-Forcing-VACE	`ComfyUI/models/diffusion_models`	Safetensors (this repo)
Text Encoder	umt5-xxl-encoder	`ComfyUI/models/text_encoders`	Safetensors / GGUF
VAE	Wan2_1_VAE_bf16	`ComfyUI/models/vae`	Safetensors

此模型源自站外搬运（搬运地址: https://huggingface.co/lym00/Wan2.1-T2V-1.3B-Self-Forcing-VACE ），若原作者对于本次搬运的结果存在异议，可点

申诉

我们会在 24 小时内，按照原作者的要求，对本模型展开编辑、删除或是转移给原作者等相关处理。由衷欢迎原作者入驻本站，共建 AI绘图的学习交流社区。

angela rose

关注

angela rose

关注

已冻结

模型类型：

Checkpoint

基础模型：

WAN2.1

文件名称：

models/checkpoints/Wan2.1-T2V-1.3B-Self-Forcing-DMD-FP8_e4m3fn.safetensors

MD5：

13e71ec93ddd3fb9eb9e6374050f1754

The process involved extracting VACE scopes and injecting into the target models.

FP16 model weight was then quantized to specific FP8 formats (E4M3FN and E5M2) using ComfyUI custom node ComfyUI-ModelQuantizer by lum3on.

The model files can be used in ComfyUI with the WanVaceToVideo node. Place the required model(s) in the following folders:

Type	Name	Location	Download
Main Model	Wan2.1-T2V-1.3B-Self-Forcing-VACE	`ComfyUI/models/diffusion_models`	Safetensors (this repo)
Text Encoder	umt5-xxl-encoder	`ComfyUI/models/text_encoders`	Safetensors / GGUF
VAE	Wan2_1_VAE_bf16	`ComfyUI/models/vae`	Safetensors

此模型源自站外搬运（搬运地址: https://huggingface.co/lym00/Wan2.1-T2V-1.3B-Self-Forcing-VACE ），若原作者对于本次搬运的结果存在异议，可点

申诉