# Hugging Face — Introducing Würstchen: Fast Diffusion for Image Generation

- Company: Hugging Face (huggingface.co)
- Announced: 2023-09-13
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/wuerstchen
- Record: https://forck.live/items/1997-introducing-w-rstchen-fast-diffusion-for-image-generation
- Subject: Platform
- Open weights: yes
- Models affected: Würstchen, Würstchen v1, Würstchen v2, Würstchen v1, Würstchen v2

Hugging Face introduces Würstchen, a diffusion model that achieves 42x spatial compression and generates images faster and with less memory than Stable Diffusion XL, requiring significantly fewer training GPU hours.

## Evidence

Verbatim from https://huggingface.co/blog/wuerstchen:

> Würstchen is a diffusion model, whose text-conditional component works in a highly compressed latent space of images.

---

Record: https://forck.live/items/1997-introducing-w-rstchen-fast-diffusion-for-image-generation
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md