SD3.5-medium-gguf Open-Source Text-to-Image Generation Model - Supports Old Devices, Enables Free Image Generation!

Sd3.5 Medium Gguf

Developed by calcuis

The GGUF quantized version of Stable Diffusion 3.5 Medium, suitable for text-to-image tasks and capable of running on legacy devices.

Image Generation EnglishOpen Source License:Other #GGUF Quantization Lightweight #Legacy Device Compatibility #Fast Text-to-Image

Downloads 3,232

Release Time : 10/30/2024

Model Overview

This is a GGUF quantized version based on the Stable Diffusion 3.5 Medium model, primarily designed for text-to-image generation tasks, with special optimizations for efficiency on resource-limited devices.

Model Features

GGUF Quantization

The model has undergone GGUF quantization, significantly reducing its size while maintaining good generation quality.

Legacy Device Compatibility

Specially optimized to run on resource-limited devices, including vintage CPUs.

Multiple Quantization Levels

Offers various quantization levels from q1_0 to q5_0 to meet different quality and performance needs.

ComfyUI Integration

Pre-configured to support ComfyUI workflows, simplifying deployment and usage.

Model Capabilities

Text-to-Image Generation

Artistic Creation

Concept Design

Image Synthesis

Use Cases

Creative Art

Digital Art Creation

Generate high-quality digital artworks based on text descriptions.

Example screenshots demonstrate good artistic effects.

Concept Design

Product Concept Visualization

Quickly transform product concepts into visual representations.

🚀 GGUF quantized version of Stable Diffusion 3.5 Medium

This is a GGUF quantized version of Stable Diffusion 3.5 Medium, enabling text - to - image generation.

🚀 Quick Start

📦 Installation

The following steps need to be done only once:

Drag sd3.5_medium-q5_0.gguf (2.02GB) 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.

💻 Usage Examples

Basic Usage

You can run the model without additional installation:

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, it's awesome!

Workflows

Example workflow for gguf (if it doesn't work, upgrade your pack: ggc y) 👻
Example workflow for the original safetensors 🎃

🔧 Technical Details

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.
By the way, 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 👍

📚 Documentation

Upper tier options

sd3.5 - large (recommended)
sd3.5 - turbo

References

Base model from stabilityai
ComfyUI from comfyanonymous
GGUF node from city96
GGUF - comfy pack

📄 License

License: other
License Name: stabilityai - ai - community
License Link: LICENSE

screenshot

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご