├── .gitignore ├── README.md ├── asset ├── case.png ├── demo_audio.wav ├── demo_video.mp4 └── structure3.png ├── demo.ipynb ├── env.txt ├── sample.py ├── stable_audio_tools ├── __init__.py ├── configs │ ├── dataset_configs │ │ ├── custom_metadata │ │ │ └── custom_md_example.py │ │ ├── local_training_example.json │ │ └── s3_wds_example.json │ ├── model_config.json │ ├── model_config_vl30.json │ ├── model_config_vl30_noabs.json │ └── model_configs │ │ ├── autoencoders │ │ ├── dac_2048_32_vae.json │ │ ├── encodec_musicgen_rvq.json │ │ ├── stable_audio_1_0_vae.json │ │ └── stable_audio_2_0_vae.json │ │ ├── dance_diffusion │ │ ├── dance_diffusion_base.json │ │ ├── dance_diffusion_base_16k.json │ │ ├── dance_diffusion_base_44k.json │ │ └── dance_diffusion_large.json │ │ └── txt2audio │ │ ├── stable_audio_1_0.json │ │ └── stable_audio_2_0.json ├── data │ ├── __init__.py │ ├── clip_feature.py │ ├── dataset.py │ └── utils.py ├── inference │ ├── __init__.py │ ├── generation.py │ ├── sampling.py │ └── utils.py ├── models │ ├── __init__.py │ ├── adp.py │ ├── autoencoders.py │ ├── blocks.py │ ├── bottleneck.py │ ├── conditioners.py │ ├── diffusion.py │ ├── dit.py │ ├── factory.py │ ├── pretrained.py │ ├── pretransforms.py │ ├── transformer.py │ └── utils.py └── training │ ├── __init__.py │ ├── autoencoders.py │ ├── diffusion.py │ ├── factory.py │ ├── losses │ ├── __init__.py │ ├── __pycache__ │ │ ├── __init__.cpython-38.pyc │ │ ├── auraloss.cpython-38.pyc │ │ └── losses.cpython-38.pyc │ ├── auraloss.py │ └── losses.py │ ├── training_wrapper.py │ └── utils.py └── train.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/.gitignore -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/README.md -------------------------------------------------------------------------------- /asset/case.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/asset/case.png -------------------------------------------------------------------------------- /asset/demo_audio.wav: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/asset/demo_audio.wav -------------------------------------------------------------------------------- /asset/demo_video.mp4: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/asset/demo_video.mp4 -------------------------------------------------------------------------------- /asset/structure3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/asset/structure3.png -------------------------------------------------------------------------------- /demo.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/demo.ipynb -------------------------------------------------------------------------------- /env.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/env.txt -------------------------------------------------------------------------------- /sample.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/sample.py -------------------------------------------------------------------------------- /stable_audio_tools/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/__init__.py -------------------------------------------------------------------------------- /stable_audio_tools/configs/dataset_configs/custom_metadata/custom_md_example.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/dataset_configs/custom_metadata/custom_md_example.py -------------------------------------------------------------------------------- /stable_audio_tools/configs/dataset_configs/local_training_example.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/dataset_configs/local_training_example.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/dataset_configs/s3_wds_example.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/dataset_configs/s3_wds_example.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_config.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_config.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_config_vl30.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_config_vl30.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_config_vl30_noabs.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_config_vl30_noabs.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/autoencoders/dac_2048_32_vae.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/autoencoders/dac_2048_32_vae.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/autoencoders/encodec_musicgen_rvq.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/autoencoders/encodec_musicgen_rvq.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/autoencoders/stable_audio_1_0_vae.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/autoencoders/stable_audio_1_0_vae.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/autoencoders/stable_audio_2_0_vae.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/autoencoders/stable_audio_2_0_vae.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base_16k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base_16k.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base_44k.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_base_44k.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_large.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/dance_diffusion/dance_diffusion_large.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/txt2audio/stable_audio_1_0.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/txt2audio/stable_audio_1_0.json -------------------------------------------------------------------------------- /stable_audio_tools/configs/model_configs/txt2audio/stable_audio_2_0.json: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/configs/model_configs/txt2audio/stable_audio_2_0.json -------------------------------------------------------------------------------- /stable_audio_tools/data/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stable_audio_tools/data/clip_feature.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/data/clip_feature.py -------------------------------------------------------------------------------- /stable_audio_tools/data/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/data/dataset.py -------------------------------------------------------------------------------- /stable_audio_tools/data/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/data/utils.py -------------------------------------------------------------------------------- /stable_audio_tools/inference/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stable_audio_tools/inference/generation.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/inference/generation.py -------------------------------------------------------------------------------- /stable_audio_tools/inference/sampling.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/inference/sampling.py -------------------------------------------------------------------------------- /stable_audio_tools/inference/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/inference/utils.py -------------------------------------------------------------------------------- /stable_audio_tools/models/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/__init__.py -------------------------------------------------------------------------------- /stable_audio_tools/models/adp.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/adp.py -------------------------------------------------------------------------------- /stable_audio_tools/models/autoencoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/autoencoders.py -------------------------------------------------------------------------------- /stable_audio_tools/models/blocks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/blocks.py -------------------------------------------------------------------------------- /stable_audio_tools/models/bottleneck.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/bottleneck.py -------------------------------------------------------------------------------- /stable_audio_tools/models/conditioners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/conditioners.py -------------------------------------------------------------------------------- /stable_audio_tools/models/diffusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/diffusion.py -------------------------------------------------------------------------------- /stable_audio_tools/models/dit.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/dit.py -------------------------------------------------------------------------------- /stable_audio_tools/models/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/factory.py -------------------------------------------------------------------------------- /stable_audio_tools/models/pretrained.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/pretrained.py -------------------------------------------------------------------------------- /stable_audio_tools/models/pretransforms.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/pretransforms.py -------------------------------------------------------------------------------- /stable_audio_tools/models/transformer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/transformer.py -------------------------------------------------------------------------------- /stable_audio_tools/models/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/models/utils.py -------------------------------------------------------------------------------- /stable_audio_tools/training/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/__init__.py -------------------------------------------------------------------------------- /stable_audio_tools/training/autoencoders.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/autoencoders.py -------------------------------------------------------------------------------- /stable_audio_tools/training/diffusion.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/diffusion.py -------------------------------------------------------------------------------- /stable_audio_tools/training/factory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/factory.py -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/__init__.py: -------------------------------------------------------------------------------- 1 | from .losses import * -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/__pycache__/__init__.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/losses/__pycache__/__init__.cpython-38.pyc -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/__pycache__/auraloss.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/losses/__pycache__/auraloss.cpython-38.pyc -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/__pycache__/losses.cpython-38.pyc: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/losses/__pycache__/losses.cpython-38.pyc -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/auraloss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/losses/auraloss.py -------------------------------------------------------------------------------- /stable_audio_tools/training/losses/losses.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/losses/losses.py -------------------------------------------------------------------------------- /stable_audio_tools/training/training_wrapper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/training_wrapper.py -------------------------------------------------------------------------------- /stable_audio_tools/training/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/stable_audio_tools/training/utils.py -------------------------------------------------------------------------------- /train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/Ceaglex/LoVA/HEAD/train.py --------------------------------------------------------------------------------