1. ComfyUI 최신버전을 받아서 설치, run_XXXX.bat파일 실행
Release v0.3.22 · comfyanonymous/ComfyUI
What's Changed fix: ltxv crop guides works with 0 keyframes by @kvochko in #7085 Full Changelog: v0.3.21...v0.3.22
github.com
2. Kijai Wan2.1을 다운로드 및 ComfyUI\custom_nodes로 이동
GitHub - kijai/ComfyUI-WanVideoWrapper
Contribute to kijai/ComfyUI-WanVideoWrapper development by creating an account on GitHub.
github.com
3. ComfyUI_windows_portable 폴더에서 아래 코드 실행
.\python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper-main\requirements.txt4. 아래 코드 다운로드 및 custom_nodes로 이동
GitHub - Kosinkadink/ComfyUI-VideoHelperSuite: Nodes related to video workflows
Nodes related to video workflows. Contribute to Kosinkadink/ComfyUI-VideoHelperSuite development by creating an account on GitHub.
github.com
5. ComfyUI_windows_portable 폴더에서 아래 코드 실행
.\python_embeded\python.exe -m pip install -r ComfyUI\custom_nodes\ComfyUI-VideoHelperSuite\requirements.txt6. 아래 사이트에서 각 모델을 다운로드 받아서 아래 폴더로 이동
- 메인 모델 : ComfyUI/models/diffusion_models
- Wan2_1-I2V-14B-480P_fp8_e4m3fn.safetensors
- Wan2_1-I2V-14B-720P_fp8_e4m3fn.safetensors
- Wan2_1-T2V-14B_fp8_e4m3fn.safetensors
- Wan2_1-T2V-1_3B_bf16.safetensors
- Wan2_1-T2V-1_3B_fp8_e4m3fn.safetensors
- VAE : ComfyUI/models/vae
- Wan2_1_VAE_bf16.safetensors
- Wan2_1_VAE_fp32.safetensors
- Text Encoder : ComfyUI/models/text_encoders
- open-clip-xlm-roberta-large-vit-huge-14_fp16.safetensors
- open-clip-xlm-roberta-large-vit-huge-14_visual_fp32.safetensors
- umt5-xxl-enc-bf16.safetensors
- umt5-xxl-enc-fp8_e4m3fn.safetensors
Kijai/WanVideo_comfy at main
huggingface.co
7. 아래 폴더로 이동하여 json 실행
ComfyUI\custom_nodes\ComfyUI-WanVideoWrapper-main\example_workflows