Manual WanFusionX Text to image Install

Manual Install Method from my last Youtube Video: https://youtu.be/oOGiYy7cTFw


# Manual Installation Guide for Wan FusionX ComfyUI

This guide will walk you through setting up ComfyUI with all the necessary custom nodes and models for the Wan FusionX workflow.

---

### **Step 1: Prerequisites**

Before you begin, ensure you have the following software installed:
*   **7-Zip:** A file archiver for extracting the ComfyUI package. Download from: https://www.7-zip.org/
*   **Git:** A version control system needed to download custom nodes. Download from: https://git-scm.com/download/win

---

### **Step 2: Download and Extract ComfyUI**

1.  Download the ComfyUI portable version for NVIDIA GPUs from the official repository:
    *   **Download Link:** https://github.com/comfyanonymous/ComfyUI/releases/download/v0.3.44/ComfyUI_windows_portable_nvidia.7z

2.  Once downloaded, use 7-Zip to extract the archive. After extraction, your folder structure should look like this:

    ```
    ComfyUI_windows_portable/
    ├── ComfyUI/
    │   ├── models/
    │   └── custom_nodes/
    ├── python_embeded/
    └── run_nvidia_gpu.bat
    ```

---

### **Step 3: Install Required Custom Nodes**

1.  Navigate to the `custom_nodes` directory:
    `ComfyUI_windows_portable\ComfyUI\custom_nodes`

2.  Open a Command Prompt or Terminal window in this folder. You can do this by typing `cmd` in the folder's address bar and pressing Enter.

3.  Run the following `git clone` commands one by one to download all the necessary nodes:

    ```cmd
    git clone https://github.com/ltdrdata/ComfyUI-Manager.git
    git clone https://github.com/Fannovel16/comfyui_controlnet_aux
    git clone https://github.com/city96/ComfyUI-GGUF
    git clone https://github.com/rgthree/rgthree-comfy
    git clone https://github.com/yolain/ComfyUI-Easy-Use
    git clone https://github.com/kijai/ComfyUI-KJNodes
    git clone https://github.com/ssitu/ComfyUI_UltimateSDUpscale
    git clone https://github.com/cubiq/ComfyUI_essentials
    git clone https://github.com/Zehong-Ma/ComfyUI-MagCache
    git clone https://github.com/wallish77/wlsh_nodes
    git clone https://github.com/vrgamegirl19/comfyui-vrgamedevgirl
    ```

4.  **IMPORTANT:** Install Python dependencies for the new nodes. Check each new folder for a `requirements.txt` file. For each one you find, run the corresponding command below from the `custom_nodes` directory:

    ```cmd
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI-Manager\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r comfyui_controlnet_aux\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI-GGUF\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r rgthree-comfy\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI-Easy-Use\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI-KJNodes\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI_UltimateSDUpscale\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI_essentials\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r ComfyUI-MagCache\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r wlsh_nodes\requirements.txt
    ..\..\python_embeded\python.exe -m pip install -r comfyui-vrgamedevgirl\requirements.txt
    ```

---

### **Step 4: Download Wan FusionX Model Files**

All required model files are hosted on Hugging Face:
**https://huggingface.co/Aitrepreneur/FLX/tree/main**

Download the files listed below and place them into the correct subdirectories inside `ComfyUI_windows_portable\ComfyUI\models\`. Create any missing folders (like `unet`, `text_encoders`, etc.).

**1. Text Encoders**
*   **Path:** `ComfyUI\models\text_encoders\`
*   **File:** `umt5-xxl-encoder-Q5_K_S.gguf`

**2. VAE**
*   **Path:** `ComfyUI\models\vae\`
*   **File:** `wan_2.1_vae.safetensors`

**3. UNets (Choose ONE set based on your GPU VRAM)**
*   **Path:** `ComfyUI\models\unet\`
*   **For GPUs < 12 GB VRAM (Q4_K_S):**
    *   `Wan14BT2VFusionX-Q4_K_S.gguf`
    *   `Wan2.1_T2V_14B_FusionX_VACE-Q4_K_S.gguf`
*   **For GPUs 12-16 GB VRAM (Q5_K_S):**
    *   `Wan14BT2VFusionX-Q5_K_S.gguf`
    *   `Wan2.1_T2V_14B_FusionX_VACE-Q5_K_S.gguf`
*   **For GPUs 16+ GB VRAM (Q8_0):**
    *   `Wan14BT2VFusionX-Q8_0.gguf`
    *   `Wan2.1_T2V_14B_FusionX_VACE-Q8_0.gguf`

**4. Optional: Original Wan UNet**
*   **Path:** `ComfyUI\models\unet\`
*   **File:** `wan2.1-t2v-14b-[YOUR_CHOSEN_VERSION].gguf` (e.g., `wan2.1-t2v-14b-Q5_K_S.gguf`)

**5. LoRAs**
*   **Path:** `ComfyUI\models\loras\`
*   **Files:**
    *   `Wan2.1_T2V_14B_FusionX_LoRA.safetensors`
    *   `Wan21_T2V_14B_lightx2v_cfg_step_distill_lora_rank32.safetensors`

**6. Upscale Models**
*   **Path:** `ComfyUI\models\upscale_models\`
*   **Files:**
    *   `4x-ClearRealityV1.pth`
    *   `RealESRGAN_x4plus_anime_6B.pth`

---

### **Step 5: Run ComfyUI**

Once all files are in place, navigate back to the main `ComfyUI_windows_portable` directory and double-click the **`run_nvidia_gpu.bat`** file to start ComfyUI.

---





Run ComfyUI




## 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