Diffusion models applied to latent spaces, which are normally built with (Variational) Autoencoders.
Source: High-Resolution Image Synthesis with Latent Diffusion ModelsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Generation | 53 | 18.09% |
Denoising | 22 | 7.51% |
Decoder | 11 | 3.75% |
Text-to-Image Generation | 10 | 3.41% |
Video Generation | 6 | 2.05% |
Image Reconstruction | 6 | 2.05% |
Virtual Try-on | 5 | 1.71% |
Image-to-Image Translation | 5 | 1.71% |
Semantic Segmentation | 5 | 1.71% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |