DanceGRPO: Unleashing GRPO on Visual Generation
Paper • 2505.07818 • Published • 34
CHINA
-
-
Wan-AI/Wan2.1-VACE-14B
Image-to-Video • 17B • Updated • 73.5k • 518 -
Qwen/Qwen2.5-Omni-7B-GPTQ-Int4
Any-to-Any • 11B • Updated • 607 • 16 -
hustvl/PixelHacker
Updated • 13 -
ByteDance-Seed/BAGEL-7B-MoT
Any-to-Any • 15B • Updated • 1k • 1.22k -
deepseek-ai/DeepSeek-R1-0528
Text Generation • 685B • Updated • 182k • • 2.47k -
ByteDance-Seed/BM-Model
Image-to-Image • Updated • 5 -
selftok-team/SelftokTokenizer
Updated • 2 -
ByteDance/XVerse
Text-to-Image • Updated • 66 • 92 -
ATH-MaaS/Ovis-U1-3B
Any-to-Any • 4B • Updated • 288 • 215 -
X-Omni/X-Omni-Zh
10B • Updated • 83 • 7 -
Qwen/Qwen-Image
Text-to-Image • 20B • Updated • 268k • • 2.67k -
Skywork/Skywork-UniPic-1.5B
Any-to-Any • Updated • 65 • 116 -
nunchaku-ai/nunchaku-qwen-image
Text-to-Image • Updated • 15.4k • 263 -
meituan-longcat/LongCat-Image
Text-to-Image • Updated • 13.7k • • 249 -
sensenova/SenseNova-U1.5-8B-MoT-Preview
Any-to-Any • 18B • Updated • 294 • 101
