🚀 JoyAI Image Edit: GGUF Setup Guide Optimize your ComfyUI workflow with the high-performance GGUF versions of JoyAI Image Edit.
🛠️ Mandatory Requirements You must have the following custom node set installed for this to function:
Node Set: ComfyUI_JoyAI_Image (by smthemex)
Installation: Search for "JoyAI" in the ComfyUI Custom Nodes Manager.
📂 Installation Path (Critical!) [!CAUTION] Both the Transformer and the Text Encoder MUST be placed in the gguf folder. Do NOT put them in unet or text_encoders.
If you don't have a gguf folder yet, create it here: ComfyUI\models\gguf\
📥 Download Links
- Transformers (Place in models/gguf) Choose the quantization level that fits your hardware:
Q6_K (High Quality / Balanced) https://huggingface.co/smthem/JoyAI-Image-Edit-merge-dit-gguf/blob/main/joy_image_transformer-Q6_K.gguf
Q8_0 (Maximum Precision) https://huggingface.co/smthem/JoyAI-Image-Edit-merge-dit-gguf/blob/main/joy_image_transformer-Q8_0.gguf
Und-Merger Text Encoder (Place in models/gguf) Text Encoder Q6_K https://huggingface.co/smthem/JoyAI-Image-Edit-merge-dit-gguf/blob/main/JoyAI-Image-Und-merger-Q6_K.gguf
VAE (Place in models/vae) Wan2.1 VAE https://huggingface.co/jdopensource/JoyAI-Image-Edit/blob/main/vae/Wan2.1_VAE.pth
📝 Quick Setup Checklist Nodes: Install ComfyUI_JoyAI_Image via Manager.
Directory: Ensure ComfyUI/models/gguf/ exists.
Placement: Move the Transformer (.gguf) and Text Encoder (.gguf) into that folder.
VAE: Move the Wan2.1_VAE.pth into models/vae/.
Restart: Refresh ComfyUI and you're ready to go.