LDM-4

Reported on 5 benchmarks across 4 tasks · 1 paper · 5 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical2 results

Image GenerationonCelebA-HQ 256x256
FID· 2021-12-20
5.11
best: 3.15 (RDM)
SOTA
High-Resolution Image Synthesis with Latent Diffusion Models arXiv:2112.10752
Image GenerationonConceptual Captions
FID· 2021-12-20
17.01
best: 9.8 (Contextual RQ-Transformer)
SOTA
High-Resolution Image Synthesis with Latent Diffusion Models arXiv:2112.10752

Audio2 results

10-shot image generationonConceptual Captions
FID· 2021-12-20
17.01
best: 9.8 (Contextual RQ-Transformer)
SOTA
High-Resolution Image Synthesis with Latent Diffusion Models arXiv:2112.10752
1 Image, 2*2 StitchionConceptual Captions
FID· 2021-12-20
17.01
best: 9.8 (Contextual RQ-Transformer)
SOTA
High-Resolution Image Synthesis with Latent Diffusion Models arXiv:2112.10752

Natural Language Processing1 result

Text-to-Image GenerationonConceptual Captions
FID· 2021-12-20
17.01
best: 9.8 (Contextual RQ-Transformer)
SOTA
High-Resolution Image Synthesis with Latent Diffusion Models arXiv:2112.10752