keisuke-okb/S2D2
S2D2: Simple Stable Diffusion based on Diffusers (Hires.fix on jupyter notebook, ipython or python interactive shell)
This tool helps digital artists and content creators generate high-quality images from text prompts without needing a complex web interface. You provide text descriptions (prompts and negative prompts) and existing Stable Diffusion model files (.safetensors) and it outputs refined, upscaled images. It's designed for users who prefer to work directly within a Python environment like a Jupyter notebook.
No commits in the last 6 months.
Use this if you are a digital artist or content creator familiar with Python and want precise control over image generation and upscaling using Stable Diffusion models, especially for 'Hires.fix' style enhancements.
Not ideal if you prefer a graphical user interface for image generation or need features like ControlNet or batch processing for multiple images simultaneously.
Stars
54
Forks
8
Language
Python
License
Apache-2.0
Category
Last pushed
Jul 12, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/keisuke-okb/S2D2"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
siliconflow/onediff
OneDiff: An out-of-the-box acceleration library for diffusion models.
wooyeolbaek/attention-map-diffusers
🚀 Cross attention map tools for huggingface/diffusers
jina-ai/discoart
🪩 Create Disco Diffusion artworks in one line
chengzeyi/stable-fast
https://wavespeed.ai/ Best inference performance optimization framework for HuggingFace...
hkproj/pytorch-stable-diffusion
Stable Diffusion implemented from scratch in PyTorch