Helios
Collection
Helios: 14B Real-Time Long Video Generation Model can be Cheaper, Faster but Keep Stronger than 1.3B ones • 7 items • Updated • 24
2026 March 🍀 - China Open Source Highlights
-
-
Qwen/Qwen3.5-0.8B
Image-Text-to-Text • 0.9B • Updated • 2.7M • 500 -
Qwen/Qwen3.5-9B
Image-Text-to-Text • 10B • Updated • 6.38M • • 1.3k -
FireRedTeam/FireRed-Image-Edit-1.1
Image-to-Image • Updated • 12.4k • 219 -
stepfun-ai/Step-3.5-Flash-Base
Text Generation • 198B • Updated • 250 • 83 -
meituan/MemOCR-7B
Visual Question Answering • 8B • Updated • 19 • 7 -
YuanLabAI/Yuan3.0-Ultra
1T • Updated • 191 • 52 -
tencent/Penguin-VL-8B
Text Generation • 9B • Updated • 3.09k • 74 -
UnipatAI/UniScientist-30B-A3B
Text Generation • 31B • Updated • 145 • 13 -
FireRedTeam/FireRed-Image-Edit-LoRA-Zoo
Updated • 40 -
fishaudio/s2-pro
Text-to-Speech • 5B • Updated • 59.3k • 865 -
FunAudioLLM/Fun-CineForge
Updated • 135 • 58 -
tencent/Covo-Audio-Chat
Audio-to-Audio • 8B • Updated • 682 • 87 -
baidu/Qianfan-OCR
Image-Text-to-Text • 5B • Updated • 194k • 1.16k -
OpenSQZ/AutoMathText-V2
Viewer • Updated • 15.2B • 67.5k • 77 -
rednote-hilab/dots.mocr
Image-Text-to-Text • 3B • Updated • 115k • 100 -
GAIR/daVinci-MagiHuman
Image-to-Video • Updated • 1.72k • 320 -
meituan-longcat/LongCat-Flash-Prover
Text Generation • 561B • Updated • 442 • 30 -
FunAudioLLM/PrismAudio
Updated • 75 -
Logics-MLLM/Logics-Parsing-Omni
32B • Updated • 173 • 9 -
meituan-longcat/LongCat-Next
Any-to-Any • 74B • Updated • 16.8k • 158 -
SII-GAIR-NLP/davinci-llm-model
Text Generation • 3B • Updated • 1.39k • 29 -
Skywork/Matrix-Game-3.0
Image-Text-to-Video • Updated • 200 • 110 -
meituan-longcat/LongCat-AudioDiT-1B
1B • Updated • 8.8k • 44 -
meituan-longcat/LongCat-AudioDiT-3.5B
4B • Updated • 5.44k • 64 -
Qwen3.5 Omni Offline Demo
🌍124Chat with a multimodal AI using text, images, audio, or video
-
robbyant/mdm_depth
Updated • 234k • 26 -
jdh-algo/JoyMed-8B-v1.0
Image-Text-to-Text • 9B • Updated • 183 • 4
