sd3.5 large gguf

Name: sd3.5 large gguf
Rating: 2.2 (61 reviews)

by calcuis

Open source · 7k downloads · 61 likes

2.2

(61 reviews)ImageAPI & Local

About

The sd3.5 large gguf model is an optimized and quantized version of Stable Diffusion 3.5 Large, designed to generate high-precision images from text descriptions with fine details. It leverages an advanced architecture capable of understanding complex prompts and producing coherent visuals, even for elaborate scenes or diverse artistic styles. Its primary use cases include artistic creation, illustration, visual concept design, and image generation for creative or professional projects. What sets it apart is its compatibility with lightweight environments thanks to its quantization, enabling accessible use on less powerful machines without compromising output quality. It also stands out for its seamless integration with tools like ComfyUI, providing a streamlined user experience for artists and creators.

Documentation

GGUF quantized version of Stable Diffusion 3.5 Large

screenshot

Setup (once)

drag sd3.5_large-q4_0.gguf (4.77GB) to > ./ComfyUI/models/unet
drag clip_g.safetensors (1.39GB) to > ./ComfyUI/models/clip
drag clip_l.safetensors (246MB) to > ./ComfyUI/models/clip
drag t5xxl_fp8_e4m3fn.safetensors (4.89GB) to > ./ComfyUI/models/clip
drag diffusion_pytorch_model.safetensors (168MB) 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 (you can find it below) to > your browser
generate your first picture with sd3, awesome!

Workflows

example workflow for gguf (demo picture shown above generated by: Q4_0 - 4.77GB)
example workflow for the original safetensors (16.5GB)

References

base model from stabilityai
comfyui from comfyanonymous
gguf node from city96
gguf-comfy pack

Capabilities & Tags

diffuserssafetensorsggufstable-diffusiongguf-comfytext-to-imageen

Links & Resources