Muse-3B (zero-shot)

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

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

Audio2 results

10-shot image generationonMS-COCO
FID· 2023-01-02
7.88
SOTA
Muse: Text-To-Image Generation via Masked Generative Transformers arXiv:2301.00704
1 Image, 2*2 StitchionMS-COCO
FID· 2023-01-02
7.88
SOTA
Muse: Text-To-Image Generation via Masked Generative Transformers arXiv:2301.00704

Medical1 result

Image GenerationonMS-COCO
FID· 2023-01-02
7.88
SOTA
Muse: Text-To-Image Generation via Masked Generative Transformers arXiv:2301.00704

Natural Language Processing1 result

Text-to-Image GenerationonMS-COCO
FID· 2023-01-02
7.88
SOTA
Muse: Text-To-Image Generation via Masked Generative Transformers arXiv:2301.00704