gguf-comfy 0.2.1

run flux1/sd3 model with beginner GPU (low cost) or even CPU

gguf-comfy

node diagram generator (image/audio/video)

enter the menu by

py -m gguf_comfy

Please select:

1. download gguf pack
2. download comfy pack

Enter your choice (1 to 2): _

gguf pack (option 1)

generic pack with gguf as core node

comfy pack (option 2)

comfy pack with gguf as custom node

• decompress the 7z bundle file: Extract All... (it includes everything you need to run a model)
• you could either get the dry run pack here or pick them one-by-one from the source below
• download flux-dev-fp32-q4_0.gguf (6.71GB); pull it to ./ComfyUI/models/diffusion_models
• download clip_l_fp32-f16.gguf (246MB) and t5xxl_fp32-q4_0.gguf (2.75GB); pull them to ./ComfyUI/models/text_encoders
• download pig_flux_vae_fp32-f16.gguf) (168MB); pull it to ./ComfyUI/models/vae
• run the .bat file under the main directory (it will activate the py backend as well as the js frontend)
• drag workflow-flux-dev.json to the activated browser

You are good to GO! (now you can run flux1 with the cheapest Nvidia GPU or merely CPU) ENJOY!

Reference: flux city96 comfyanonymous gguf

Stable Diffusion 3.5 is now supported (please upgrade to the latest version)

Run sd3.x model following the step-by-step guide below:

• you could either get the backup pack here or pick them one-by-one from the original source below
• download sd3.5_large-q4_0.gguf (4.77GB); pull it to ./ComfyUI/models/diffusion_models
• download clip_g.safetensors (1.39GB), clip_l.safetensors (234MB), and t5xxl_fp8_e4m3fn.safetensors (4.55GB); pull them all to ./ComfyUI/models/text_encoders
• download diffusion_pytorch_model.safetensors (168MB); pull it to ./ComfyUI/models/vae
• run the .bat file under the main directory (it will activate the py backend as well as the js frontend)
• drag workflow-gguf-sd3.5.json to the activated browser

Reference: stability-ai gguf