├── .gitignore ├── LICENSE ├── README.md ├── assets └── teaser.png ├── examples ├── audio1.wav ├── man_Jaime.png └── test_case.json ├── humo ├── common │ ├── __init__.py │ ├── config.py │ ├── distributed │ │ ├── __init__.py │ │ ├── advanced.py │ │ └── basic.py │ └── logger.py ├── configs │ ├── inference │ │ ├── generate.yaml │ │ └── generate_1_7B.yaml │ └── models │ │ ├── Wan_1.3B.yaml │ │ ├── Wan_1.3B_I2V.yaml │ │ ├── Wan_14B.yaml │ │ └── Wan_14B_I2V.yaml ├── generate.py ├── generate_1_7B.py ├── models │ ├── audio │ │ └── audio_proj.py │ ├── distributed │ │ ├── __init__.py │ │ ├── dit_ulysses_sequence_parallel.py │ │ └── fsdp.py │ ├── text │ │ └── encoder.py │ ├── utils │ │ ├── fm_solvers.py │ │ ├── fm_solvers_unipc.py │ │ └── utils.py │ └── wan_modules │ │ ├── __init__.py │ │ ├── attention.py │ │ ├── clip.py │ │ ├── model.py │ │ ├── model_humo.py │ │ ├── t5.py │ │ ├── tokenizers.py │ │ ├── vae.py │ │ └── xlm_roberta.py └── utils │ ├── audio_processor_whisper.py │ └── wav2vec.py ├── main.py ├── requirements.txt └── scripts ├── infer_ta.sh ├── infer_ta_1_7B.sh ├── infer_tia.sh └── infer_tia_1_7B.sh /.gitignore: -------------------------------------------------------------------------------- 1 | .DS_Store 2 | __pycache__ 3 | .idea 4 | .vscode 5 | *.log 6 | /weights 7 | /output -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/README.md -------------------------------------------------------------------------------- /assets/teaser.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/assets/teaser.png -------------------------------------------------------------------------------- /examples/audio1.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/examples/audio1.wav -------------------------------------------------------------------------------- /examples/man_Jaime.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/examples/man_Jaime.png -------------------------------------------------------------------------------- /examples/test_case.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/examples/test_case.json -------------------------------------------------------------------------------- /humo/common/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /humo/common/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/common/config.py -------------------------------------------------------------------------------- /humo/common/distributed/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/common/distributed/__init__.py -------------------------------------------------------------------------------- /humo/common/distributed/advanced.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/common/distributed/advanced.py -------------------------------------------------------------------------------- /humo/common/distributed/basic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/common/distributed/basic.py -------------------------------------------------------------------------------- /humo/common/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/common/logger.py -------------------------------------------------------------------------------- /humo/configs/inference/generate.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/inference/generate.yaml -------------------------------------------------------------------------------- /humo/configs/inference/generate_1_7B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/inference/generate_1_7B.yaml -------------------------------------------------------------------------------- /humo/configs/models/Wan_1.3B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/models/Wan_1.3B.yaml -------------------------------------------------------------------------------- /humo/configs/models/Wan_1.3B_I2V.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/models/Wan_1.3B_I2V.yaml -------------------------------------------------------------------------------- /humo/configs/models/Wan_14B.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/models/Wan_14B.yaml -------------------------------------------------------------------------------- /humo/configs/models/Wan_14B_I2V.yaml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/configs/models/Wan_14B_I2V.yaml -------------------------------------------------------------------------------- /humo/generate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/generate.py -------------------------------------------------------------------------------- /humo/generate_1_7B.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/generate_1_7B.py -------------------------------------------------------------------------------- /humo/models/audio/audio_proj.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/audio/audio_proj.py -------------------------------------------------------------------------------- /humo/models/distributed/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /humo/models/distributed/dit_ulysses_sequence_parallel.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/distributed/dit_ulysses_sequence_parallel.py -------------------------------------------------------------------------------- /humo/models/distributed/fsdp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/distributed/fsdp.py -------------------------------------------------------------------------------- /humo/models/text/encoder.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/text/encoder.py -------------------------------------------------------------------------------- /humo/models/utils/fm_solvers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/utils/fm_solvers.py -------------------------------------------------------------------------------- /humo/models/utils/fm_solvers_unipc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/utils/fm_solvers_unipc.py -------------------------------------------------------------------------------- /humo/models/utils/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/utils/utils.py -------------------------------------------------------------------------------- /humo/models/wan_modules/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/__init__.py -------------------------------------------------------------------------------- /humo/models/wan_modules/attention.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/attention.py -------------------------------------------------------------------------------- /humo/models/wan_modules/clip.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/clip.py -------------------------------------------------------------------------------- /humo/models/wan_modules/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/model.py -------------------------------------------------------------------------------- /humo/models/wan_modules/model_humo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/model_humo.py -------------------------------------------------------------------------------- /humo/models/wan_modules/t5.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/t5.py -------------------------------------------------------------------------------- /humo/models/wan_modules/tokenizers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/tokenizers.py -------------------------------------------------------------------------------- /humo/models/wan_modules/vae.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/vae.py -------------------------------------------------------------------------------- /humo/models/wan_modules/xlm_roberta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/models/wan_modules/xlm_roberta.py -------------------------------------------------------------------------------- /humo/utils/audio_processor_whisper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/utils/audio_processor_whisper.py -------------------------------------------------------------------------------- /humo/utils/wav2vec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/humo/utils/wav2vec.py -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/main.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/requirements.txt -------------------------------------------------------------------------------- /scripts/infer_ta.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/scripts/infer_ta.sh -------------------------------------------------------------------------------- /scripts/infer_ta_1_7B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/scripts/infer_ta_1_7B.sh -------------------------------------------------------------------------------- /scripts/infer_tia.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/scripts/infer_tia.sh -------------------------------------------------------------------------------- /scripts/infer_tia_1_7B.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Phantom-video/HuMo/HEAD/scripts/infer_tia_1_7B.sh --------------------------------------------------------------------------------