|
--- |
|
license: other |
|
license_name: stabilityai-ai-community |
|
license_link: LICENSE |
|
language: |
|
- en |
|
base_model: |
|
- stabilityai/stable-diffusion-3.5-large-turbo |
|
pipeline_tag: image-to-text |
|
tags: |
|
- stable-diffusion |
|
- gguf-comfy |
|
--- |
|
# GGUF quantized version of Stable Diffusion 3.5 Large Turbo |
|
|
|
## Setup example |
|
- drag sd3.5_large_turbo-q4_0.gguf (4.44GB) to > ./ComfyUI/models/unet |
|
- drag [clip_g.safetensors](https://huggingface.co/calcuis/sd3.5-large-gguf/blob/main/clip_g.safetensors) (1.39GB) to > ./ComfyUI/models/clip |
|
- drag [clip_l.safetensors](https://huggingface.co/calcuis/sd3.5-large-gguf/blob/main/clip_l.safetensors) (246MB) to > ./ComfyUI/models/clip |
|
- drag [t5xxl_fp8_e4m3fn.safetensors](https://huggingface.co/calcuis/sd3.5-large-gguf/blob/main/t5xxl_fp8_e4m3fn.safetensors) (4.89GB) to > ./ComfyUI/models/clip |
|
- drag [diffusion_pytorch_model.safetensors](https://huggingface.co/calcuis/sd3.5-large-gguf/blob/main/diffusion_pytorch_model.safetensors) (168MB) to > ./ComfyUI/models/vae |
|
|
|
## Run it straight (no installation needed) |
|
- run the .bat file in the main directory (assuming you are using the gguf-comfy pack below) |
|
- drag the workflow json file (you can find it below) to > your browser |
|
- generate your first picture with sd3, awesome! |
|
|
|
### Workflows |
|
- example workflow for [gguf](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5t-gguf.json) |
|
- example workflow for the original [safetensors](https://github.com/calcuis/comfy/blob/main/workflow-sd3.5t-safetensors.json) (15.3GB) |
|
|
|
### References |
|
- base model from [stabilityai](https://huggingface.co/stabilityai/stable-diffusion-3.5-large-turbo) |
|
- 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) |
|
|
|
 |
|
|
|
demo picture above is from base model |
|
|
|
 |
|
|
|
these two figures are from base model as well |
|
|
