๐Ÿงจ Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e

๐Ÿ“ฐ Hugging Face Blog

Accelerate Stable Diffusion XL inference with JAX on Cloud TPU v5e for faster performance

advanced Published 3 Oct 2023
Action Steps
  1. Understand the basics of Stable Diffusion XL and JAX
  2. Set up a Cloud TPU v5e instance
  3. Install and configure JAX for use with Cloud TPU v5e
  4. Optimize Stable Diffusion XL inference with JAX on Cloud TPU v5e
Who Needs to Know This

AI engineers and researchers can benefit from this article to improve the performance of their Stable Diffusion XL models, while developers and DevOps teams can learn about the integration of JAX and Cloud TPU v5e

Key Insight

๐Ÿ’ก Using JAX with Cloud TPU v5e can significantly accelerate Stable Diffusion XL inference

Share This
๐Ÿš€ Accelerate Stable Diffusion XL inference with JAX on Cloud TPU v5e! ๐Ÿค–

Key Takeaways

Accelerate Stable Diffusion XL inference with JAX on Cloud TPU v5e for faster performance

Full Article

Published Time: 2023-10-03T00:00:00.294Z

# ๐Ÿงจ Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e

[![Image 1: Hugging Face's logo](https://huggingface.co/front/assets/huggingface_logo-noborder.svg)Hugging Face](https://huggingface.co/)

* [Models](https://huggingface.co/models)
* [Datasets](https://huggingface.co/datasets)
* [Spaces](https://huggingface.co/spaces)
* [Buckets new](https://huggingface.co/storage)
* [Docs](https://huggingface.co/docs)
* [Enterprise](https://huggingface.co/enterprise)
* [Pricing](https://huggingface.co/pricing)
*
*
* * *

* [Log In](https://huggingface.co/login)
* [Sign Up](https://huggingface.co/join)

[Back to Articles](https://huggingface.co/blog)

# [](https://huggingface.co/blog/sdxl_jax#accelerating-stable-diffusion-xl-inference-with-jax-on-cloud-tpu-v5e) Accelerating Stable Diffusion XL Inference with JAX on Cloud TPU v5e

Published October 3, 2023

[Update on GitHub](https://github.com/huggingface/blog/blob/main/sdxl_jax.md)

[- [x] Upvote 9](https://huggingface.co/login?next=%2Fblog%2Fsdxl_jax)
* [![Image 2](https://cdn-avatars.huggingface.co/v1/production/uploads/1679301626301-61a5e575dc7a70d5a225be8e.jpeg)](https://huggingface.co/hsyntemiz "hsyntemiz")
* [![Image 3](https://huggingface.co/avatars/a3ac6acb2dd58554d052a56ed113d518.svg)](https://huggingface.co/Vinzou "Vinzou")
* [![Image 4](https://cdn-avatars.huggingface.co/v1/production/uploads/1675922559338-noauth.png)](https://huggingface.co/CrypterG "CrypterG")
* [![Image 5](https://huggingface.co/avatars/42b6d569f84f62b037227ffbd2de0865.svg)](https://huggingface.co/Yanihartz "Yanihartz")
* [![Image 6](https://cdn-avatars.huggingface.co/v1/production/uploads/6581f9514adaee05cf640f81/sXvEEraq2QlSIyWHlSmpa.jpeg)](https://huggingface.co/xi0v "xi0v")
* [![Image 7](https://huggingface.co/avatars/18c9808d0a4d7c22ea3756f8f8fcd53d.svg)](https://huggingface.co/Gared-Jih "Gared-Jih")
* +3

[![Image 8: Pedro Cuenca's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1617264212503-603d25b75f9d390ab190b777.jpeg)](https://huggingface.co/pcuenq)

[Pedro Cuenca pcuenq Follow](https://huggingface.co/pcuenq)

[![Image 9: Juan Acevedo's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/64db82b81855ce11cd5b0471/oURwbWuW8fNRD_brD13QU.jpeg)](https://huggingface.co/jffacevedo)

[Juan Acevedo jffacevedo Follow](https://huggingface.co/jffacevedo)

guest

[![Image 10: Alex Spiridonov's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/6511d9f9c915724a6534a3af/a9kxhCyXb3YbIPTpaF-Id.png)](https://huggingface.co/alexspiridonov)

[Alex Spiridonov alexspiridonov Follow](https://huggingface.co/alexspiridonov)

guest

[![Image 11: Pate Motter's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/6511b211ec53a754ff355955/V0qUBi1RHVrF9znxJ8PEV.jpeg)](https://huggingface.co/pmotter)

[Pate Motter pmotter Follow](https://huggingface.co/pmotter)

guest

[![Image 12: Yavuz Yetim's avatar](https://huggingface.co/avatars/18bd17450d3dcf8315e98f017f6e1d57.svg)](https://huggingface.co/yyetim)

[Yavuz Yetim yyetim Follow](https://huggingface.co/yyetim)

guest

[![Image 13: Vaibhav Singh's avatar](https://huggingface.co/avatars/9c181eb76062efd5518cdc305da1191f.svg)](https://huggingface.co/svaibhav)

[Vaibhav Singh svaibhav Follow](https://huggingface.co/svaibhav)

guest

[![Image 14: Vijaya Singh's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/6511c98d367ce825b1dc40bd/nHdreps0nGuYglj_Cg64K.jpeg)](https://huggingface.co/vjsingh)

[Vijaya Singh vjsingh Follow](https://huggingface.co/vjsingh)

guest

[![Image 15: Patrick von Platen's avatar](https://cdn-avatars.huggingface.co/v1/production/uploads/1584435275418-5dfcb1aada6d0311fd3d5448.jpeg)](https://huggingface.co/patrickvonplaten)

[Patrick von Platen patrickvonplaten Follow](https://huggingface.co/patrickvonplaten)

* [Why JAX + TPU v5e for SDXL?](https://huggingface.co/blog/sdxl_jax#why-jax--tp
Read full article โ†’ โ† Back to Reads

Related Videos

5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
MCP explained for beginners
MCP explained for beginners
Withmesravani_
Temperature Explained | Why ChatGPT Gives Different Answers | AI Series Day 14 #Shorts
Temperature Explained | Why ChatGPT Gives Different Answers | AI Series Day 14 #Shorts
Withmesravani_
4 Generative AI Projects That Will Get You Hired in 2026 ๐Ÿš€
4 Generative AI Projects That Will Get You Hired in 2026 ๐Ÿš€
SCALER
I Tested My AI-Powered Autocoder With 3 Different LLM Models
I Tested My AI-Powered Autocoder With 3 Different LLM Models
Making Made Easy
You Can Run Your Own Powerful LLM AI On Almost Any Computer! OPEN SOURCE! NO GPU NEEDED! MISTRAL 7B!
You Can Run Your Own Powerful LLM AI On Almost Any Computer! OPEN SOURCE! NO GPU NEEDED! MISTRAL 7B!
Making Made Easy