Updated: Jan 30, 2026
style
Workflow for Qwen models image. To debug all nodes, first run Workflow customization. Update and install process nodes. If there are errors, you need to look at the ComfyUI load. You can try a full cache clear. Run cmd or powershell # Go to the ComfyUI root # 1. Delete ALL pycache folders and .pyc files in ALL custom nodes # 2. Delete the ComfyUI Manager cache (it often stores service information) # 3. (Optional) You can clear the ComfyUI interface cache. The neural network will write the code for you, save it. If this doesn't work, try updating your libraries. Update pip and packages. If you're using portable versions, update from your update folder - update_comfyui_and_python_dependencies.
Model 1 - design SDXL - v1.0 | Stable Diffusion XL Checkpoint | Civitai
Model 2 - Nova Furry XL - IL v15.5 | Illustrious Checkpoint | Civitai
Take the newest model.
Model 3 Flux1-Dev-SRPO-v1-Q8_0.gguf · wikeeyang/SRPO-Refine-Quantized-v1.0 at main
or flux1-dev-fp8_11GB - flux1-dev-fp8_11GB_RFS_2 | Flux Checkpoint | Civitai
Lora to choose from for different models. Search for add-detail-xl