# Runway — High-Resolution Image Synthesis with Latent Diffusion Models

- Company: Runway (runway.com)
- Announced: 2022-04-13T16:32:44.214000+00:00
- Category: research-paper
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://runway.com/research/high-resolution-image-synthesis-with-latent-diffusion-models
- Record: https://forck.live/items/7943-high-resolution-image-synthesis-with-latent-diffusion-models
- Subject: Gen / Aleph

Runway researchers introduced latent diffusion models (LDMs) that apply diffusion in the latent space of pretrained autoencoders, using cross-attention layers for conditioning inputs such as text or bounding boxes. LDMs achieve competitive performance on unconditional image generation, inpainting, and super-resolution while reducing computational requirements compared to pixel-based diffusion models.

## Evidence

Verbatim from https://runway.com/research/high-resolution-image-synthesis-with-latent-diffusion-models:

> By decomposing the image formation process into a sequential application of denoising autoencoders, diffusion models (DMs) achieve state-of-the-art synthesis results on image data and beyond. ... Our latent diffusion models (LDMs) achieve highly competitive performance on various tasks, including unconditional image generation, inpainting, and super-resolution, while significantly reducing computational requirements compared to pixel-based DMs.

---

Record: https://forck.live/items/7943-high-resolution-image-synthesis-with-latent-diffusion-models
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md