Manual Comfyui Wan Models Install

Manual Install Method from my last Youtube Video: https://youtu.be/H8Ky0LhRaGs

1. Download and extract the ComfyUI portable version from:
   https://github.com/comfyanonymous/ComfyUI

2. After extraction, you should have this folder structure:
   ```
   ComfyUI_windows_portable/
   ├── ComfyUI/
   │   ├── models/
   │   └── custom_nodes/
   ├── python_embeded/
   └── run_nvidia_gpu.bat
   ```

## Custom Nodes Installation

Navigate to `ComfyUI_windows_portable/ComfyUI/custom_nodes` and clone these repositories:


git clone https://github.com/ltdrdata/ComfyUI-Manager.git
git clone https://github.com/logtd/ComfyUI-LTXTricks
git clone https://github.com/pythongosssss/ComfyUI-Custom-Scripts
git clone https://github.com/theUpsider/ComfyUI-Logic


## Core WAN Models

LINKS TO ALL MODELS:

https://huggingface.co/Kijai/WanVideo_comfy/tree/main
https://huggingface.co/Comfy-Org/Wan_2.1_ComfyUI_repackaged/tree/main/split_files
https://huggingface.co/city96/Wan2.1-I2V-14B-480P-gguf/tree/main
https://huggingface.co/city96/Wan2.1-T2V-14B-gguf/tree/main
https://huggingface.co/city96/Wan2.1-I2V-14B-720P-gguf/tree/main

### 1. Text-to-Video Models

models/checkpoints/
ltx-video-2b-v0.9-fp8_e4m3fn.safetensors



models/vae/
wan_2.1_vae.safetensors
LTX_vae.safetensors
hunyuan_video_vae_bf16.safetensors


models/text_encoders/
umt5_xxl_fp8_e4m3fn_scaled.safetensors


models/unet/ (CHOOSE ONE):
wan2.1-t2v-14b-Q4_K_S.gguf (12GB VRAM)
wan2.1-t2v-14b-Q5_K_S.gguf (16GB VRAM)
wan2.1-t2v-14b-Q8_0.gguf (24GB+ VRAM)


wan2.1-i2v-14b-480p-{MODEL_VERSION}.gguf
wan2.1-i2v-14b-720p-{MODEL_VERSION}.gguf

fast-hunyuan-video-t2v-720p-{MODEL_VERSION}.gguf

ltx-video-2b-v0.9-{MODEL_VERSION}.gguf

skyreels-hunyuan-I2V-{MODEL_VERSION}.gguf


models/clip_vision/
clip_vision_h.safetensors




models/clip/
t5xxl_fp16.safetensors
clip_l.safetensors
llava_llama3_fp8_scaled.safetensors


models/diffusion_models/
skyreels_hunyuan_i2v_fp8_e4m3fn.safetensors
wan2.1_t2v_1.3B_bf16.safetensors


models/upscale_models/
4x-ClearRealityV1.pth


## RunPod Installation

1. Create account at: https://bit.ly/runpodAi
2. Choose a 24GB VRAM GPU with the aitrepreneur/comfyui template
3. Access port 8888
4. Follow the same folder structure as above
5. Use `curl` to download files:

   curl -L -o "filename" "URL"

6. Monitor logs with:

   tail -f workspace/logs/comfyui.log