# Stable Diffusion 1.4

- Date: 2022-08-22
- Type: model
- Credit: CompVis (LMU Munich) · Stability AI · Runway
- Image: https://aifilmhistory.org/carousel/stable-diffusion-1-4/compvis-0005-0.jpg
- URL: https://aifilmhistory.org/entry/stable-diffusion-1-4

In August 2022 Stability AI released the weights of Stable Diffusion 1.4, commercial use allowed. Built by Robin Rombach and Patrick Esser's CompVis group in Munich, it ran diffusion in a compressed latent space, so it ran on a consumer graphics card. Unlike DALL·E 2 and Midjourney, it could be downloaded, fine-tuned, and bolted onto anything.

For filmmakers the key was img2img: feed it a frame, nudge the output, feed it back, and you have animation. The [Deforum notebook](https://aifilmhistory.org/entry/deforum/) turned that loop into a tool, and ControlNet, AnimateDiff, and [Stable Video Diffusion](https://aifilmhistory.org/entry/stable-video-diffusion/) grew from it. Every open-weight video model since has followed the path 1.4 cleared.

Links:
- Wikipedia — Stable Diffusion: https://en.wikipedia.org/wiki/Stable_Diffusion
- Stability AI — Stable Diffusion Public Release (Aug 22, 2022): https://stability.ai/news/stable-diffusion-public-release
- CompVis/stable-diffusion on GitHub: https://github.com/CompVis/stable-diffusion
- Model card — CompVis/stable-diffusion-v1-4 (Hugging Face): https://huggingface.co/CompVis/stable-diffusion-v1-4
- Paper — High-Resolution Image Synthesis with Latent Diffusion Models (arXiv): https://arxiv.org/abs/2112.10752
- NightCafe — creations made with Stable Diffusion 1.4: https://creator.nightcafe.studio/model/stable-diffusion-v1/creations
- LAION-5B: https://laion.ai/blog/laion-5b/

---
Source: https://aifilmhistory.org/entry/stable-diffusion-1-4
Era: 2022 · The Dawn
Last updated: 2026-09-12