DanceGRPO: Unleashing GRPO on Visual Generation
Paper
•
2505.07818
•
Published
•
32
CHINA
-
-
Wan-AI/Wan2.1-VACE-14B
Image-to-Video • Updated • 3.5k • 488 -
Qwen/Qwen2.5-Omni-7B-GPTQ-Int4
Any-to-Any • 11B • Updated • 18.8k • 12 -
hustvl/PixelHacker
Updated • 8 -
ByteDance-Seed/BAGEL-7B-MoT
Any-to-Any • 15B • Updated • 586 • 1.18k -
deepseek-ai/DeepSeek-R1-0528
Text Generation • 685B • Updated • 424k • • 2.39k -
ByteDance-Seed/BM-Model
Image-to-Image • Updated • 3 -
selftok-team/SelftokTokenizer
Updated • 2 -
ByteDance/XVerse
Text-to-Image • Updated • 53 • 89 -
AIDC-AI/Ovis-U1-3B
Any-to-Any • 4B • Updated • 1.85k • 212 -
X-Omni/X-Omni-Zh
Updated • 160 • 7 -
Qwen/Qwen-Image
Text-to-Image • Updated • 225k • • 2.36k -
Skywork/Skywork-UniPic-1.5B
Any-to-Any • Updated • 54 • 114 -
nunchaku-ai/nunchaku-qwen-image
Text-to-Image • Updated • 40.9k • 251 -
meituan-longcat/LongCat-Image
Text-to-Image • Updated • 53.4k • • 230
