|
--- |
|
license: other |
|
license_name: stabilityai-ai-community |
|
license_link: LICENSE |
|
language: |
|
- en |
|
base_model: |
|
- stabilityai/stable-diffusion-3.5-large |
|
pipeline_tag: text-to-image |
|
tags: |
|
- stable-diffusion |
|
- gguf-comfy |
|
--- |
|
|
|
# GGUF quantized version of Stable Diffusion 3.5 Large |
|
|
|
 |
|
|
|
## Setup (once) |
|
- drag sd3.5_large-q4_0.gguf (4.77GB) > ./ComfyUI/models/unet |
|
- drag clip_g.safetensors (1.39GB) > ./ComfyUI/models/clip |
|
- drag clip_l.safetensors (234MB) > ./ComfyUI/models/clip |
|
- drag t5xxl_fp8_e4m3fn.safetensors (4.55GB) > ./ComfyUI/models/clip |
|
- drag diffusion_pytorch_model.safetensors (168MB) > ./ComfyUI/models/vae |
|
|
|
## Run it straight (no installation needed way) |
|
- run the .bat file in the main directory (assuming you are using the gguf-comfy pack below) |
|
- drag the workflow file (you can find it below) > your browser |
|
- generate your first picture with sd3, awesome! |
|
|
|
### Workflows |
|
- example workflow for [gguf](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5-gguf.json) (demo picture shown above: Q4_0 - 4.77GB) |
|
- example workflow for the original [safetensors](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5-safetensors.json) (16.5GB) |
|
|
|
### References |
|
- base model from [stabilityai](https://huggingface.co/stabilityai/stable-diffusion-3.5-large) |
|
- comfyui from [comfyanonymous](https://github.com/comfyanonymous/ComfyUI) |
|
- gguf node from [city96](https://github.com/city96/ComfyUI-GGUF) |
|
- gguf-comfy [pack](https://github.com/calcuis/gguf-comfy/releases) |
