mediapipe==0.10.21 opencv-python>=4.9.0.80 numpy>=1.23.5,<2

# ComfyUI DreamID-V Wrapper
A simple and efficient ComfyUI integration for DreamID-V.
DreamID-V is a model for Identity-Preserving Video Generation—it animates a reference image using motion from a pose video.
bf16, fp16, etc. for best performance on your hardware.ComfyUI/custom_nodes.pip install -r requirements.txt.dreamidv.pth -> models/diffusion_models.Wan2.1_VAE.pth -> models/vae.umt5-xxl-enc-bf16.pth -> models/text_encoders.bf16).DreamID-V 的 ComfyUI 简易整合包。
DreamID-V 是一款 ID保持视频生成 模型,它能根据一张参考图和一段骨架动作,生成保持人物身份且动作一致的视频。
主打简单易用,无需复杂配置即可体验高质量的人物视频生成。
bf16、fp16 等多种精度选择,适配不同显卡。custom_nodes 目录下克隆本项目。pip install -r requirements.txt 安装依赖。dreamidv.pth 放入 models/diffusion_models。Wan2.1_VAE.pth 放入 models/vae。umt5-xxl-enc-bf16.pth 放入 models/text_encoders。bf16)。Wrapper for DreamID-V.
Original code by Bytedance and The Alibaba Wan Team.