From the source

Exploring simple optimizations for SDXL

Image published with the post by Hugging Face — Image from huggingface.co

Simple optimizations for Stable Diffusion XL (SDXL) to improve inference speed and reduce memory usage, including lower precision (fp16), memory-efficient attention (SDPA), and torch.compile.

From the source
To explore how we can optimize SDXL for inference speed and memory use, we ran some tests on an A100 GPU (40 GB).
huggingface.co

Other stories

Hugging Face · 8 Oct

The model that didn't exist, so you made it yourself

A user creates six custom models via ML Intern in days

Hugging Face · 2 OctResearch paper

AutoSynthData: Generating Training Data for Enterprise Agents

Turning model failures into training data for enterprise agents

Hugging Face · 30 Sep

Open TTS Leaderboard: Scalable Evaluation for Multilingual Text-to-Speech and Voice Cloning

Announced: 24 Oct 2023
Detected: 03 Aug 2026 21:12 UTC (+1013d after)

ModelsStable Diffusion XL, SDXL, stable-diffusion-xl-base-1.0

Visit source ↗huggingface.co

Objective metrics for TTS evaluation, complementing human preference arenas.

LG AI Research · 24 OctResearch paper

[ICML 2023] Conference Review and the Latest Research Trends

Openv0: The Open-Source, AI-Driven Generative UI Component Framework
Replit · 23 Oct
Frontier Model Forum updates
OpenAI · 25 OctPartnership