High-Resolution Image Synthesis with Latent Diffusion Models (Stable Diffusion)
by CompVis / Stability AI · open-source · Last verified 2026-03-17
Introduced Latent Diffusion Models (LDMs), which perform the diffusion process in a compressed latent space rather than pixel space, dramatically reducing computational cost while maintaining image quality. This work underpins Stable Diffusion, the most widely used open-source image generation model.
https://arxiv.org/abs/2112.10752 ↗A
A—Great
Adoption: A+Quality: A+Freshness: B+Citations: A+Engagement: F
Specifications
- License
- CreativeML Open RAIL-M
- Pricing
- open-source
- Capabilities
- text-to-image, image-to-image, inpainting, super-resolution
- Integrations
- huggingface, stability-ai-api, automatic1111
- Use Cases
- creative-image-generation, design, art-creation, research
- API Available
- Yes
- Tags
- stable-diffusion, latent-diffusion, text-to-image, generative-ai, open-source
- Added
- 2026-03-17
- Completeness
- 100%
Index Score
82Adoption
98
Quality
95
Freshness
73
Citations
95
Engagement
0
Put AI to work for your business
Deploy this paper alongside autonomous AaaS agents that handle tasks end-to-end — no babysitting required.