sayakpaul/xla-benchmark-sd
Provides code to serialize the different models involved in Stable Diffusion as SavedModels and to compile them with XLA.
This project helps machine learning engineers and researchers accelerate the inference speed of Stable Diffusion models. It takes the individual components of a KerasCV Stable Diffusion model, processes them into optimized SavedModels, and then compiles these with XLA to output significantly faster image generation. This allows for quicker experimentation and deployment of generative AI applications.
No commits in the last 6 months.
Use this if you are a machine learning engineer working with Stable Diffusion in TensorFlow and need to optimize the speed of image generation for research or production.
Not ideal if you are looking for a high-level API for Stable Diffusion without needing to delve into model compilation and optimization.
Stars
7
Forks
3
Language
Python
License
—
Category
Last pushed
Feb 27, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/sayakpaul/xla-benchmark-sd"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Isi-dev/Google-Colab_Notebooks
A Collection of Google Colab Notebooks for various projects
licyk/sd-webui-all-in-one
支持部署多种 WebUI 的 Jupyter Notebook / CLI，与支持一键部署 SD-Trainer，InvokeAI，ComfyUI，SD...
anxety-solo/sdAIgen
A1111, ComfyUI, Forge, Forge-Classic/Neo, ReForge, SD-UX - One NoteBook for Google Colab & Kaggle
shirooo39/MiXLab
Yet another multi-purpose Colab Notebook
vijishmadhavan/SkinDeep
Get Deinked!!