Views
No views yet
| Model | Status | Link |
|---|---|---|
| SAMA-5B | Coming soon | Coming soon |
| SAMA-14B | Available | syxbb/SAMA-14B |
1git clone https://github.com/Cynthiazxy123/SAMA
2cd SAMA
3
4conda create -n sama python=3.10 -y
5conda activate sama
6
7pip install --upgrade pip
8pip install -r requirements.txtWan2.1-T2V-14B model directory.infer_sh/run_sama.shMODEL_ROOTSTATE_DICTSRC_VIDEOPROMPTOUTPUT_DIRbash infer_sh/run_sama.shoutputs/seed_1/<input_video_filename>1models/
2├── Wan2.1-T2V-14B/
3│ ├── diffusion_pytorch_model-00001-of-00006.safetensors
4│ ├── diffusion_pytorch_model-00002-of-00006.safetensors
5│ ├── diffusion_pytorch_model-00003-of-00006.safetensors
6│ ├── diffusion_pytorch_model-00004-of-00006.safetensors
7│ ├── diffusion_pytorch_model-00005-of-00006.safetensors
8│ ├── diffusion_pytorch_model-00006-of-00006.safetensors
9│ ├── models_t5_umt5-xxl-enc-bf16.pth
10│ ├── Wan2.1_VAE.pth
11│ └── google/
12└── SAMA-14B/
13 └── <downloaded_checkpoint>.safetensors4k+1 frame requirement used by Wan video inference.--fps.--model-root is incomplete, the script will stop and report the missing files or directories.1@misc{zhang2026samafactorizedsemanticanchoring,
2 title={SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing},
3 author={Xinyao Zhang and Wenkai Dong and Yuxin Song and Bo Fang and Qi Zhang and Jing Wang and Fan Chen and Hui Zhang and Haocheng Feng and Yu Lu and Hang Zhou and Chun Yuan and Jingdong Wang},
4 year={2026},
5 eprint={2603.19228},
6 archivePrefix={arXiv},
7 primaryClass={cs.CV},
8 url={https://arxiv.org/abs/2603.19228},
9}