Stable Diffusion 3 Medium  

Stable Diffusion 3 Mid is a text-to-image model called Multimodal Diffusion Transformer (MMDiT). It has significant improvements in image quality, typography, understanding complex prompts, and being resource-efficient.

For more technical details, please refer to the Research paper.

Model Description

• Developed by: Stability AI
• Model type: MMDiT text-to-image generative model
• Model Description: This is a model that can be used to generate images based on text prompts. It is a Multimodal Diffusion Transformer (https://arxiv.org/abs/2403.03206) that uses three fixed, pretrained text encoders (OpenCLIP-ViT/G, CLIP-ViT/L and T5-xxl)

HOW TO RUN:

if you have a NVIDIA gpu:

run_nvidia_gpu.bat

To run it in slow CPU mode:

run_cpu.bat

IF YOU GET A RED ERROR IN THE UI MAKE SURE YOU HAVE A MODEL/CHECKPOINT IN: ComfyUI\models\checkpoints

You can download the stable diffusion 1.5 one from: https://huggingface.co/runwayml/stable-diffusion-v1-5/blob/main/v1-5-pruned-emaonly.ckpt

RECOMMENDED WAY TO UPDATE:
To update the ComfyUI code: update\update_comfyui.bat

To update ComfyUI with the python dependencies, note that you should ONLY run this if you have issues with python dependencies.
update\update_comfyui_and_python_dependencies.bat

TO SHARE MODELS BETWEEN COMFYUI AND ANOTHER UI:
In the ComfyUI directory you will find a file: extra_model_paths.yaml.example
Rename this file to: extra_model_paths.yaml and edit it with your favorite text editor.

Download:

new_ComfyUI_windows_portable_nvidia_cu121_or_cpu.7z