Dimensionality Reduction
Latent Diffusion Model
Introduced by Rombach et al. in High-Resolution Image Synthesis with Latent Diffusion ModelsDiffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.
Source: High-Resolution Image Synthesis with Latent Diffusion ModelsPapers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Generation | 53 | 17.55% |
| Denoising | 23 | 7.62% |
| Decoder | 13 | 4.30% |
| Text-to-Image Generation | 10 | 3.31% |
| Video Generation | 7 | 2.32% |
| Virtual Try-on | 6 | 1.99% |
| Image Reconstruction | 6 | 1.99% |
| Super-Resolution | 5 | 1.66% |
| Image-to-Image Translation | 5 | 1.66% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
