Top open video models
Video models for generation, classification, and video understanding.
How this list works: ranked by Hugging Face downloads in the last 30 days, among models with 1,000+ downloads.
| # | Model | Author | Downloads (30 days) | Likes | Size | License | Commercial use | Runs on |
|---|---|---|---|---|---|---|---|---|
| 1 | Wan_2.1_ComfyUI_repackaged | Comfy-Org | 4.3M | 1K | – | Apache 2.0 | Yes | CPU or GPU |
| 2 | videomae-base | MCG-NJU | 376.2K | 59 | – | CC BY-NC 4.0 | No | GPU |
| 3 | vjepa2-vitl-fpc64-256 | 317.1K | 215 | – | MIT | Yes | GPU | |
| 4 | xclip-base-patch16-zero-shot | microsoft | 176.6K | 31 | – | MIT | Yes | GPU |
| 5 | Minimax-H3-ComfyUI | Alissonerdx | 153.2K | 472 | – | Custom (other) | Check the license | CPU or GPU |
| 6 | Sulphur-2-base | SulphurAI | 117.1K | 2.2K | – | Not stated | Check the license | CPU |
| 7 | videomae-base-finetuned-kinetics | MCG-NJU | 107.1K | 52 | – | CC BY-NC 4.0 | No | GPU |
| 8 | vjepa2-vitg-fpc64-256 | 94.5K | 60 | – | Apache 2.0 | Yes | GPU | |
| 9 | xclip-base-patch32 | microsoft | 82.9K | 123 | – | MIT | Yes | GPU |
| 10 | MiniMax-H3-Character-Swap-LoRA | akatz-ai | 80.3K | 540 | – | Custom (other) | Check the license | CPU or GPU |
| 11 | vivit-b-16x2-kinetics400 | 47.9K | 44 | – | MIT | Yes | GPU | |
| 12 | vivit-b-16x2 | 41.5K | 18 | – | MIT | Yes | GPU | |
| 13 | videomae-large-finetuned-kinetics | MCG-NJU | 36.4K | 13 | – | CC BY-NC 4.0 | No | GPU |
| 14 | xclip-large-patch14 | microsoft | 19.5K | 19 | – | MIT | Yes | GPU |
| 15 | timesformer-base-finetuned-k400 | 16.6K | 46 | – | CC BY-NC 4.0 | No | GPU | |
| 16 | VideoMAEv2-Base | OpenGVLab | 16.5K | 19 | – | CC BY-NC 4.0 | No | GPU |
| 17 | vjepa2-vitl-fpc16-256-ssv2 | 14.8K | 17 | – | MIT | Yes | GPU | |
| 18 | xclip-base-patch32-16-frames | microsoft | 13.4K | 9 | – | MIT | Yes | GPU |
| 19 | timesformer-base-finetuned-k600 | 12.8K | 14 | – | CC BY-NC 4.0 | No | GPU | |
| 20 | Minimax-H3-T2VA-Veda-8NFE-600Step-Preview | Veda-Sparse | 11K | 104 | – | Custom (other) | Check the license | CPU or GPU |
| 21 | xclip-base-patch16 | microsoft | 10.5K | 9 | – | MIT | Yes | GPU |
| 22 | kandinsky-videomae-large-camera-motion | ai-forever | 8.7K | 6 | – | Not stated | Check the license | GPU |
| 23 | LTX-2.5-22b-IC-LoRA-Alpha-Gen | Lightricks | 8.3K | 149 | 22B | Custom (other) | Check the license | CPU or GPU |
| 24 | ms-eff-gcvit-deepfake-b0-ff-plus-plus | KoreaPeter | 6.7K | 2 | – | MIT | Yes | GPU |
| 25 | vjepa2-vitl-fpc16-256-ssv2 | qubvel-hf | 6.6K | 7 | – | MIT | Yes | GPU |
Other model comparisons
Top open language modelsTop open image modelsTop open audio modelsTop open embedding modelsTop open multimodal modelsTop open text-generation models (LLMs)Top open text-to-image modelsTop open text-to-speech modelsTop open speech-recognition modelsTop open feature-extraction modelsTop open sentence-similarity modelsTop open image-to-text modelsTop open vision-language modelsTop open image-classification modelsTop open image-segmentation modelsTop open object-detection modelsTop open depth-estimation modelsTop open audio-classification modelsTop open video-classification models