tencent/HunyuanVideo
Text-to-Video
•
Updated
•
1.42k
•
•
2.03k
🎬 Video models
text-to-video & image-to-video models released by the Chinese community
Note 13B parameters: Probably the largest open video model to date 👀
-
zai-org/CogVideoX-5b
Text-to-Video • Updated • 36.1k • • 640 -
zai-org/CogVideoX-2b
Text-to-Video • Updated • 24.6k • 335 -
zai-org/CogVideoX1.5-5B-SAT
Image-to-Video • Updated • 153 -
tencent/DepthCrafter
Depth Estimation • Updated • 23.6k • 99 -
hpcai-tech/OpenSora-VAE-v1.2
0.4B • Updated • 33.2k • 57 -
ByteDance/AnimateDiff-Lightning
Text-to-Video • Updated • 37.7k • 959 -
DAMO-NLP-SG/VideoLLaMA2-7B
Visual Question Answering • 8B • Updated • 449 • 41 -
ECNU-CILab/ExVideo-SVD-128f-v1
Updated • 61 -
ali-vilab/text-to-video-ms-1.7b
Text-to-Video • Updated • 13.5k • 639 -
maxin-cn/Latte-1
Text-to-Video • Updated • 2.96k • 21 -
LanguageBind/Open-Sora-Plan-v1.2.0
Updated • 2 • 47 -
Qwen/Qwen2-VL-7B-Instruct
Image-Text-to-Text • 8B • Updated • 497k • • 1.22k -
zai-org/CogVideoX-5b-I2V
Image-to-Video • Updated • 43.7k • 296
LanguageBind/Open-Sora-Plan-v1.3.0
Text-to-Video • Updated • 1 • 72Note This project aims to create a simple and scalable repo, to reproduce Sora
hpcai-tech/Open-Sora
Updated • 187Note Open-Sora, an initiative dedicated to efficiently produce high-quality video and make the model, tools and contents accessible to all.
maxin-cn/Latte
Updated • 40Note Latte: Latent Diffusion Transformer for Video Generation
-
rain1011/pyramid-flow-sd3
Text-to-Video • Updated • 831 -
DAMO-NLP-SG/VideoLLaMA2-7B-16F
Visual Question Answering • 8B • Updated • 427 • 15 -
TIGER-Lab/VideoScore
Visual Question Answering • 8B • Updated • 137 • 7 -
openbmb/VisRAG-Ret
Feature Extraction • 3B • Updated • 766 • 69 -
BAAI/Aquila-VL-2B-llava-qwen
Visual Question Answering • 2B • Updated • 1.01k • 61
