| # Matrix-Game 2 inference/runtime dependencies. | |
| # TensorRT/ONNX conversion-only packages from upstream requirements.txt are | |
| # intentionally excluded because inference.py uses demo_utils/vae_block3.py, | |
| # not demo_utils/vae.py or demo_utils/vae_torch2trt.py. | |
| torch>=2.4.0 | |
| torchvision>=0.19.0 | |
| opencv-python>=4.9.0.80 | |
| diffusers | |
| transformers>=4.49.0 | |
| tokenizers>=0.20.3 | |
| accelerate>=1.1.1 | |
| tqdm | |
| imageio | |
| easydict | |
| ftfy | |
| dashscope | |
| imageio-ffmpeg | |
| numpy<2 | |
| wandb | |
| omegaconf | |
| einops | |
| av | |
| safetensors | |
| open_clip_torch | |
| starlette | |
| pycocotools | |
| lmdb | |
| matplotlib | |
| sentencepiece | |
| pydantic | |
| scikit-image | |
| huggingface_hub[cli] | |
| dominate | |
| flask | |
| flask-socketio | |
Xet Storage Details
- Size:
- 621 Bytes
- Xet hash:
- d80ef41f0a4151d2ca8d296a2575e7c99da1cc4b65fd7178b12474f274b9d44e
·
Xet efficiently stores files, intelligently splitting them into unique chunks and accelerating uploads and downloads. More info.