# Hugging Face — VQ-Diffusion

- Company: Hugging Face (huggingface.co)
- Announced: 2022-11-30
- Category: new-model
- Coverage: not counted
- Announcement: yes
- Group: models
- Source: https://huggingface.co/blog/vq-diffusion
- Record: https://forck.live/items/2127-vq-diffusion
- Subject: Platform
- Models affected: VQ-Diffusion

VQ-Diffusion is a conditional latent diffusion model developed by the University of Science and Technology of China and Microsoft that operates on a quantized latent space using a VQ-VAE encoder and an encoder-decoder transformer.

## Evidence

Verbatim from https://huggingface.co/blog/vq-diffusion:

> Vector Quantized Diffusion (VQ-Diffusion) is a conditional latent diffusion model developed by the University of Science and Technology of China and Microsoft. Unlike most commonly studied diffusion models, VQ-Diffusion's noising and denoising processes operate on a quantized latent space, i.e., the latent space is composed of a discrete set of vectors.

---

Record: https://forck.live/items/2127-vq-diffusion
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md