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

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

其他

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

This is a merge of gdhe17/Self-Forcing and Wan-AI/Wan2.1-VACE-1.3B scopes.

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.

Usage

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

TypeNameLocationDownload
Main ModelWan2.1-T2V-1.3B-Self-Forcing-VACEComfyUI/models/diffusion_modelsSafetensors (this repo)
Text Encoderumt5-xxl-encoderComfyUI/models/text_encodersSafetensors / GGUF
VAEWan2_1_VAE_bf16ComfyUI/models/vaeSafetensors
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

angela rose

其他

模型信息

模型类型：
Checkpoint
基础模型：
WAN2.1

This is a merge of gdhe17/Self-Forcing and Wan-AI/Wan2.1-VACE-1.3B scopes.

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.

Usage

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

TypeNameLocationDownload
Main ModelWan2.1-T2V-1.3B-Self-Forcing-VACEComfyUI/models/diffusion_modelsSafetensors (this repo)
Text Encoderumt5-xxl-encoderComfyUI/models/text_encodersSafetensors / GGUF
VAEWan2_1_VAE_bf16ComfyUI/models/vaeSafetensors
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。