---
license: other
license_name: stabilityai-ai-community
license_link: LICENSE
language:
- en
base_model:
- stabilityai/stable-diffusion-3.5-medium
pipeline_tag: text-to-image
tags:
- stable-diffusion
- gguf-comfy
---

# GGUF quantized version of Stable Diffusion 3.5 Medium

![screenshot](https://raw.githubusercontent.com/calcuis/comfy/master/sd3.5g.png)

## Setup (once)
- drag sd3.5_medium-q5_0.gguf ([2.02GB](https://huggingface.co/calcuis/sd3.5-medium-gguf/blob/main/sd3.5_medium-q5_0.gguf)) to > ./ComfyUI/models/unet
- drag clip_g.safetensors ([1.39GB](https://huggingface.co/calcuis/sd3.5-medium-gguf/blob/main/clip_g.safetensors)) to > ./ComfyUI/models/clip
- drag clip_l.safetensors ([246MB](https://huggingface.co/calcuis/sd3.5-medium-gguf/blob/main/clip_l.safetensors)) to > ./ComfyUI/models/clip
- drag t5xxl_fp8_e4m3fn.safetensors ([4.89GB](https://huggingface.co/calcuis/sd3.5-medium-gguf/blob/main/t5xxl_fp8_e4m3fn.safetensors)) to > ./ComfyUI/models/clip
- drag diffusion_pytorch_model.safetensors ([168MB](https://huggingface.co/calcuis/sd3.5-medium-gguf/blob/main/diffusion_pytorch_model.safetensors)) to > ./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 json file (see below) to > your browser
- generate your first picture with sd3, awesome!

### Workflows
- example workflow for [gguf](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5m-gguf.json) (if it doesn't work, upgrade your pack: ggc y) 👻
- example workflow for the original [safetensors](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5m-safetensors.json) 🎃

### Bug reports (or brief review)
- t/q1_0 and t/q2_0; not working recently (invalid GGMLQ type error)
- q2_k is super fast; not usable; but might be good for medical research or abstract painter
- q3 family is fast; finger issue can be easily detected but picture quality is interestingly good
- btw, q3 family is usable; just need some effort on +/- prompt(s); good for old machine user
- notice the same file size in some quantized models; but they are different (according to its SHA256 hash) even they are exactly the same in size; still keep them all here (in full set); see who can deal with it
- q4 and above should be no problem for general-to-high quality production (demo picture shown above generated by just Q4_0 - 1.74GB); and sd team is pretty considerable, though you might not think this model is useful if you have good hardware; imagine you can run it with merely an ancient CPU, should probably appreciate their great effort; good job folks, thumbs up 👍

### Upper tier options
- sd3.5-[large](https://huggingface.co/calcuis/sd3.5-large-gguf) (recommended)
- sd3.5-[turbo](https://huggingface.co/calcuis/sd3.5-large-turbo)

### References
- base model from [stabilityai](https://huggingface.co/stabilityai/stable-diffusion-3.5-medium)
- 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)