Hugging Face Diffusers 0.3 released: image-to-image, Textual Inversion and low-VRAM optimization
Original title:What's new in Diffusers? 🎨
AI summary
Hugging Face releases diffusers 0.3, adding image-to-image, Textual Inversion, experimental inpainting, ONNX export and macOS M1/M2 inference support to the diffusion model library. After optimization, Stable Diffusion VRAM usage drops to 3.2GB at the cost of about 10% speed loss; the community also contributed video generation, interpretability tools and fine-tuned models for Japanese and anime directions.
Key Takeaways
- Hugging Face releases diffusers 0.
- 3,adding image-to-image,Textual Inversion,experimental inpainting,ONNX export and macOS M1/M2…
- After optimization,Stable Diffusion VRAM usage drops to 3.
- 2GB at the cost of about 10% speed loss
- the community also contributed video generation,interpretability tools and fine-tuned models for…
Quick Facts
- Published
- Updated
- Source
- Hugging Face 社区博客(混合发现)
- Category
- Products & Apps
- AI score
- 75
原文梳理了 diffusers 0.3 的图生图、Textual Inversion、低显存优化等新功能,开源图像工作流的使用者可以对照更新自己的用法。
Related entities
Source & copyright
This article is based on curated titles and AI summaries from the AIHOT public API, with attribution and links back. Original copyright remains with the original publishers and authors; this site does not mirror full texts.
How to Cite
When citing this article, keep the title, date, and permalink, and credit Orange News as the source.
Orange News: Hugging Face Diffusers 0.3 released: image-to-image, Textual Inversion and low-VRAM optimization. September 12, 2022. https://new.nat6.net/en/news/dyj20dokyl1n0oqznt5ymaoxj/