Omni1307/OmniCustom

By Omni1307 · ↓ 0 · ♥ 2 · Updated 2026-02-13

What's in this repo

This page lists the files in Omni1307/OmniCustom, including 1k3d68.onnx, 2d106det.onnx, genderage.onnx and more.

8 ONNX models (.onnx files)
589 files, including 226 .py, 90 .pyc, 53 .jpg, 24 .md, 24 .lock, 24 .metadata
Last updated 2026-02-13

ONNX files

File	Size	Download
ckpts/InsightFace/models/antelopev2/1k3d68.onnx	—	Download
ckpts/InsightFace/models/antelopev2/2d106det.onnx	—	Download
ckpts/InsightFace/models/antelopev2/genderage.onnx	—	Download
ckpts/InsightFace/models/antelopev2/glintr100.onnx	—	Download
ckpts/InsightFace/models/antelopev2/scrfd_10g_bnkps.onnx	—	Download
ckpts/LivePortrait/pretrained_weights/insightface/models/buffalo_l/2d106det.onnx	—	Download
ckpts/LivePortrait/pretrained_weights/insightface/models/buffalo_l/det_10g.onnx	—	Download
ckpts/LivePortrait/pretrained_weights/liveportrait/landmark.onnx	—	Download

How to use

These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.

README

OmniCustom: Sync Audio-Video Customization Via Joint Audio-Video Generation Model

🔥 Latest News!

Feb 12, 2026: We proposed OmniCustom, a novel framework to deal with sync audio-video customization. For more video demos, please visit the project page.
Feb 14, 2026: The inference code and the model checkpoint are publicly available.

🎥 Video

Your browser does not support the video tag.

📖 Overview

Given a reference image Ir and a reference audio Ar, our OmniCustom framework synchronously generates a video that preserves the visual identity from Ir and an audio track that mimics the timbre of Ar. Here, the speech content can be freely specified through a textual prompt.

⚡️ Quickstart

Installation

1.Clone the repo:

git clone https://github.com/OmniCustom-project/OmniCustom.git
cd OmniCustom

2. Create Environment:

conda create -n omnicustom python=3.10
conda activate omnicustom
pip install -r requirements.txt

3. Install Flash Attention :

pip install flash-attn --no-build-isolation

Model Download

First, you need to download the original model of OVI, Wan2.2-TI2V-5B, and MMAudio. You can download them using download_weights.py, and put them into ckpts:

python3 download_weights.py --output-dir ./ckpts

Models	Download Link	Notes
OmniCustom models	🤗 Huggingface	1.9G
Naturalspeech 3	🤗 Huggingface	timbre embedding extractor
InsightFace	🤗 Huggingface	face embedding extractor
LivePortrait	🤗 Huggingface	crop reference image

Then, please download the model of our OmniCustom, Naturalspeech 3, InsightFace, and LivePortrait from Huggingface, and put them into ckpts. Here, we provide a unified download command to download these four models from Huggingface.

pip install "huggingface_hub[cli]"
huggingface-cli download Omni1307/OmniCustom \
  --include "ckpts/**" \
  --local-dir ./ \
  --local-dir-use-symlinks False

The final structure of the ckpts directory should be:

# OmniCustom/ckpts 
ckpts/
├── InsightFace/
├── LivePortrait/
├── MMAudio/
├── naturalspeech3_facodec/
├── Ovi/
├── step-92000.safetensors
└── Wan2.2-TI2V-5B/

⚙️ Configure OmniCustom

The configure file of OmniCustom OmniCustom/configs/inference/inference_fusion.yaml can be modified. The following parameters control generation quality, video resolution, and how text, image, and audio inputs are balanced:

ckpt_name: Ovi/model.safetensors  #base model
lora_path: ./ckpts/step-92000.safetensors #the checkpoint of our OmniCustom
self_lora: true 
# face embedder 
face_embedder_ckpt_dir: ./ckpts/InsightFace  
face_ip_emb_dim: 512   
# audio embedder
audio_embedder_ckpt_dir: ./ckpts/naturalspeech3_facodec
audio_ip_emb_dim: 256 
# output
output_dir: ./outputs/
sample_steps: 50  # number of denoising steps. Lower (30-40) = faster generation
solver_name: unipc  # sampling algorithm for denoising process
shift: 5.0    #timestep shift factor for sampling scheduler
sp_size: 1
audio_guidance_scale: 3.0
video_guidance_scale: 4.0
mode: "id2v"                                                  # ["id2v", "t2v", "i2v", "t2i2v"] all comes with audio
fp8: False                        # load fp8 version of model, will have quality degradation and will not have speed 
cpu_offload: False
seed: 102                    # random seed for reproducible results
crop_face: true        # crop face region from the reference image
video_negative_prompt: "jitter, bad hands, blur, distortion, two people, two persons, aerial view, overexposed, low quality, deformation, a poor composition, bad hands, bad teeth, bad eyes, bad limbs, distortion, blurring, text, subtitles, static, picture, black border" 
audio_negative_prompt: "robotic, muffled, echo, distorted"    # avoid artifacts in audio
video_frame_height_width: [576, 992] #[512, 992]                         # only useful if mode = t2v or t2i2v, recommended values: [512, 992], [992, 512], [960, 512], [512, 960], [720, 720], [448, 1120]
text_prompt: ./example_prompts/benchmark_example.csv  #group generation
slg_layer: 11
each_example_n_times: 1

🔑 Inference

Single GPU

bash ./inference.sh

Or run:

CUDA_VISIBLE_DEVICES=0  infer.py --config-file ./configs/inference/inference_fusion.yaml

💡Note:

text_prompt in configs/inference/inference_fusion.yaml can change examples for sync audio-video customization. text_prompt supports a CSV file, which contains text_prompt, ip_image_path, and ip_audio_path.

Those results without any customization and those with only identity customization will be saved to the result folder.

When the generated video is unsatisfactory, the most straightforward solution is to try changing the seed in configs/inference/inference_fusion.yaml.

The Peak VRAM Required is 80 GB in a single GPU.

More Results

  Reference Images | 
  Reference Audios | 
  Text prompts | 
  Generated Videos | 





  
  
    ![Reference Image 1](https://raw.githubusercontent.com/OmniCustom-project/OmniCustom/main/assets/images/ref_68.png)
   | 
  
    
    [![Play Audio 1](https://img.shields.io/badge/🔊-Play%20Audio%201-1e88e5?style=for-the-badge)](https://github.com/user-attachments/assets/281b285a-80bc-482e-a62b-6f1cce389c6a)
   | 
  
    
      A man stands at the podium in OpenAI's luxurious conference room, behind him a massive electronic screen displays the company's glowing profit data. He grips the microphone firmly, gazes across the audience below, and announces in a steady tone: &lt;S&gt;The board wants to sell OpenAI to Zuckerberg, which is unacceptable.&lt;E&gt;
    

   | 
  
    
    [![Watch Video 1](https://img.shields.io/badge/▶️-Watch%20Video%201-764ba2?style=for-the-badge)](https://github.com/user-attachments/assets/5472ec3d-57bc-45b3-a921-7913d0bd8bb7)
   | 



  
  
    ![Reference Image 2](https://raw.githubusercontent.com/OmniCustom-project/OmniCustom/main/assets/images/ref_69.png)
   | 
  
    [![Play Audio 2](https://img.shields.io/badge/🔊-Play%20Audio%202-1e88e5?style=for-the-badge)](https://github.com/user-attachments/assets/a6294f38-ba3a-449c-b8e3-8fce181124fe)
   | 
  
    
      A woman stands before the iconic Rockefeller Center Christmas Tree, its thousands of lights reflecting in her eyes as snow begins to fall gently around her. Wearing a tartan scarf and holding a cup of steaming cocoa, she brings her mittened hands together and speaks softly into the frosty air: &lt;S&gt;May the spirit of Christmas fill your heart throughout the coming year.&lt;E&gt;
    

   | 
  
    [![Watch Video 2](https://img.shields.io/badge/▶️-Watch%20Video%202-764ba2?style=for-the-badge)](https://github.com/user-attachments/assets/1ba22392-705c-42c7-a00b-073925c37b37)
   | 



  
  
    ![Reference Image 3](https://raw.githubusercontent.com/OmniCustom-project/OmniCustom/main/assets/images/ref_70.png)
   | 
  
    [![Play Audio 3](https://img.shields.io/badge/🔊-Play%20Audio%203-1e88e5?style=for-the-badge)](https://github.com/user-attachments/assets/d7399bc5-60cb-4d6e-9af2-06306694e4f2)
   | 
  
    
      A man stands on a bustling street in Shanghai, the air thick with the festive atmosphere of Chinese Lunar New Year, with numerous red lanterns hanging in clusters overhead. He blends seamlessly into the vibrant surroundings, then clasps his hands together in a traditional gesture of greeting and says warmly: &lt;S&gt;Wishing everyone a Happy New Year and joy every single day.&lt;E&gt;
    

   | 
  
    [![Watch Video 3](https://img.shields.io/badge/▶️-Watch%20Video%203-764ba2?style=for-the-badge)](https://github.com/user-attachments/assets/1925cc0b-1ab5-4ce7-b6c9-33a64152d195)
   |

📑 Todo List

[x] Inference Codes and Checkpoint of OmniCustom
[ ] Open Source Evaluation Benchmark
[ ] Open Source OmniCustom-1M dataset
[ ] Training Codes of OmniCustom

🙏 Acknowledgements

We would like to thank the following projects:

OVI: Our OmniCustom is finetuned over OVI for ID and timbre customization.

Naturalspeech 3: 256-D timbre embeddings are extracted using Naturalspeech 3.

InsightFace: 512-D face embeddings are extracted using InsightFace.

LivePortrait: Crop reference image for better ID Customization.

MMAudio: Audio VAE is provided by MMAudio.

Wan2.2: The video branch is initialized from the Wan2.2 repository.

⭐

If OmniCustom is helpful, please help to ⭐ the repo.

📚 Citation

We will link the paper soon.

Model info

onnx region:us

↓ 0 ♥ 2

Created: 2026-02-09

Updated: 2026-02-13

View on Hugging Face

Files (589)

.gitattributes

.gitignore

README.md

assets/icon.jpg

assets/images/ref_68.png

assets/images/ref_69.png

assets/images/ref_70.png

assets/images/teaser.png

ckpts/InsightFace/models/antelopev2/.gitattributes

ckpts/InsightFace/models/antelopev2/1k3d68.onnx ONNX

ckpts/InsightFace/models/antelopev2/2d106det.onnx ONNX

ckpts/InsightFace/models/antelopev2/genderage.onnx ONNX

ckpts/InsightFace/models/antelopev2/glintr100.onnx ONNX

ckpts/InsightFace/models/antelopev2/scrfd_10g_bnkps.onnx ONNX

ckpts/LivePortrait/.gitignore

ckpts/LivePortrait/.vscode/settings.json

ckpts/LivePortrait/LICENSE

ckpts/LivePortrait/app.py

ckpts/LivePortrait/app_animals.py

ckpts/LivePortrait/assets/.gitignore

ckpts/LivePortrait/assets/docs/LivePortrait-Gradio-2024-07-19.jpg

ckpts/LivePortrait/assets/docs/animals-mode-gradio-2024-08-02.jpg

ckpts/LivePortrait/assets/docs/changelog/2024-07-10.md

ckpts/LivePortrait/assets/docs/changelog/2024-07-19.md

ckpts/LivePortrait/assets/docs/changelog/2024-07-24.md

ckpts/LivePortrait/assets/docs/changelog/2024-08-02.md

ckpts/LivePortrait/assets/docs/changelog/2024-08-05.md

ckpts/LivePortrait/assets/docs/changelog/2024-08-06.md

ckpts/LivePortrait/assets/docs/changelog/2024-08-19.md

ckpts/LivePortrait/assets/docs/changelog/2025-01-01.md

ckpts/LivePortrait/assets/docs/directory-structure.md

ckpts/LivePortrait/assets/docs/driving-option-multiplier-2024-08-02.jpg

ckpts/LivePortrait/assets/docs/editing-portrait-2024-08-06.jpg

ckpts/LivePortrait/assets/docs/how-to-install-ffmpeg.md

ckpts/LivePortrait/assets/docs/image-driven-image-2024-08-19.jpg

ckpts/LivePortrait/assets/docs/image-driven-portrait-animation-2024-08-19.jpg

ckpts/LivePortrait/assets/docs/inference-animals.gif

ckpts/LivePortrait/assets/docs/inference.gif

ckpts/LivePortrait/assets/docs/pose-edit-2024-07-24.jpg

ckpts/LivePortrait/assets/docs/retargeting-video-2024-08-02.jpg

ckpts/LivePortrait/assets/docs/showcase.gif

ckpts/LivePortrait/assets/docs/showcase2.gif

ckpts/LivePortrait/assets/docs/speed.md

ckpts/LivePortrait/assets/examples/driving/aggrieved.pkl

ckpts/LivePortrait/assets/examples/driving/d0.mp4

ckpts/LivePortrait/assets/examples/driving/d1.pkl

ckpts/LivePortrait/assets/examples/driving/d10.mp4

ckpts/LivePortrait/assets/examples/driving/d11.mp4

ckpts/LivePortrait/assets/examples/driving/d12.jpg

ckpts/LivePortrait/assets/examples/driving/d12.mp4

ckpts/LivePortrait/assets/examples/driving/d13.mp4

ckpts/LivePortrait/assets/examples/driving/d14.mp4

ckpts/LivePortrait/assets/examples/driving/d18.mp4

ckpts/LivePortrait/assets/examples/driving/d19.jpg

ckpts/LivePortrait/assets/examples/driving/d19.mp4

ckpts/LivePortrait/assets/examples/driving/d2.pkl

ckpts/LivePortrait/assets/examples/driving/d20.mp4

ckpts/LivePortrait/assets/examples/driving/d3.mp4

ckpts/LivePortrait/assets/examples/driving/d30.jpg

ckpts/LivePortrait/assets/examples/driving/d38.jpg

ckpts/LivePortrait/assets/examples/driving/d5.pkl

ckpts/LivePortrait/assets/examples/driving/d6.mp4

ckpts/LivePortrait/assets/examples/driving/d7.pkl

ckpts/LivePortrait/assets/examples/driving/d8.jpg

ckpts/LivePortrait/assets/examples/driving/d8.pkl

ckpts/LivePortrait/assets/examples/driving/d9.jpg

ckpts/LivePortrait/assets/examples/driving/d9.mp4

ckpts/LivePortrait/assets/examples/driving/laugh.pkl

ckpts/LivePortrait/assets/examples/driving/open_lip.pkl

ckpts/LivePortrait/assets/examples/driving/shake_face.pkl

ckpts/LivePortrait/assets/examples/driving/shy.pkl

ckpts/LivePortrait/assets/examples/driving/talking.pkl

ckpts/LivePortrait/assets/examples/driving/wink.pkl

ckpts/LivePortrait/assets/examples/source/s0.jpg

ckpts/LivePortrait/assets/examples/source/s1.jpg

ckpts/LivePortrait/assets/examples/source/s10.jpg

ckpts/LivePortrait/assets/examples/source/s11.jpg

ckpts/LivePortrait/assets/examples/source/s12.jpg

ckpts/LivePortrait/assets/examples/source/s13.mp4

ckpts/LivePortrait/assets/examples/source/s18.mp4

ckpts/LivePortrait/assets/examples/source/s2.jpg

ckpts/LivePortrait/assets/examples/source/s20.mp4

ckpts/LivePortrait/assets/examples/source/s22.jpg

ckpts/LivePortrait/assets/examples/source/s23.jpg

ckpts/LivePortrait/assets/examples/source/s25.jpg

ckpts/LivePortrait/assets/examples/source/s29.mp4

ckpts/LivePortrait/assets/examples/source/s3.jpg

ckpts/LivePortrait/assets/examples/source/s30.jpg

ckpts/LivePortrait/assets/examples/source/s31.jpg

ckpts/LivePortrait/assets/examples/source/s32.jpg

ckpts/LivePortrait/assets/examples/source/s32.mp4

ckpts/LivePortrait/assets/examples/source/s33.jpg

ckpts/LivePortrait/assets/examples/source/s36.jpg

ckpts/LivePortrait/assets/examples/source/s38.jpg

ckpts/LivePortrait/assets/examples/source/s39.jpg

ckpts/LivePortrait/assets/examples/source/s4.jpg

ckpts/LivePortrait/assets/examples/source/s40.jpg

ckpts/LivePortrait/assets/examples/source/s41.jpg

ckpts/LivePortrait/assets/examples/source/s42.jpg

ckpts/LivePortrait/assets/examples/source/s5.jpg

ckpts/LivePortrait/assets/examples/source/s6.jpg

ckpts/LivePortrait/assets/examples/source/s7.jpg

ckpts/LivePortrait/assets/examples/source/s8.jpg

ckpts/LivePortrait/assets/examples/source/s9.jpg

ckpts/LivePortrait/assets/gradio/gradio_description_animate_clear.md

ckpts/LivePortrait/assets/gradio/gradio_description_animation.md

ckpts/LivePortrait/assets/gradio/gradio_description_retargeting.md

ckpts/LivePortrait/assets/gradio/gradio_description_retargeting_video.md

ckpts/LivePortrait/assets/gradio/gradio_description_upload.md

ckpts/LivePortrait/assets/gradio/gradio_description_upload_animal.md

ckpts/LivePortrait/assets/gradio/gradio_title.md

ckpts/LivePortrait/inference.py

ckpts/LivePortrait/inference_animals.py

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/.gitignore

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitattributes.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitattributes.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitignore.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitignore.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitkeep.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/.gitkeep.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/README.md.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/README.md.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/docs/inference.gif.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/docs/inference.gif.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/docs/showcase2.gif.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/docs/showcase2.gif.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/insightface/models/buffalo_l/2d106det.onnx.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/insightface/models/buffalo_l/2d106det.onnx.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/insightface/models/buffalo_l/det_10g.onnx.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/insightface/models/buffalo_l/det_10g.onnx.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/appearance_feature_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/appearance_feature_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/motion_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/motion_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/spade_generator.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/spade_generator.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/warping_module.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/base_models/warping_module.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/landmark.onnx.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/landmark.onnx.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/retargeting_models/stitching_retargeting_module.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait/retargeting_models/stitching_retargeting_module.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/appearance_feature_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/appearance_feature_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/motion_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/motion_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/spade_generator.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/spade_generator.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/warping_module.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models/warping_module.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/appearance_feature_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/appearance_feature_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/motion_extractor.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/motion_extractor.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/spade_generator.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/spade_generator.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/warping_module.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/base_models_v1.1/warping_module.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/retargeting_models/stitching_retargeting_module.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/retargeting_models/stitching_retargeting_module.pth.metadata

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/xpose.pth.lock

ckpts/LivePortrait/pretrained_weights/.cache/huggingface/download/liveportrait_animals/xpose.pth.metadata

ckpts/LivePortrait/pretrained_weights/.gitattributes

ckpts/LivePortrait/pretrained_weights/.gitignore

ckpts/LivePortrait/pretrained_weights/.gitkeep

ckpts/LivePortrait/pretrained_weights/README.md

ckpts/LivePortrait/pretrained_weights/docs/inference.gif

ckpts/LivePortrait/pretrained_weights/docs/showcase2.gif

ckpts/LivePortrait/pretrained_weights/insightface/models/buffalo_l/2d106det.onnx ONNX

ckpts/LivePortrait/pretrained_weights/insightface/models/buffalo_l/det_10g.onnx ONNX

ckpts/LivePortrait/pretrained_weights/liveportrait/base_models/appearance_feature_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait/base_models/motion_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait/base_models/spade_generator.pth

ckpts/LivePortrait/pretrained_weights/liveportrait/base_models/warping_module.pth

ckpts/LivePortrait/pretrained_weights/liveportrait/landmark.onnx ONNX

ckpts/LivePortrait/pretrained_weights/liveportrait/retargeting_models/stitching_retargeting_module.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models/appearance_feature_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models/motion_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models/spade_generator.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models/warping_module.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models_v1.1/appearance_feature_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models_v1.1/motion_extractor.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models_v1.1/spade_generator.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/base_models_v1.1/warping_module.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/retargeting_models/stitching_retargeting_module.pth

ckpts/LivePortrait/pretrained_weights/liveportrait_animals/xpose.pth

ckpts/LivePortrait/readme.md

ckpts/LivePortrait/readme_zh_cn.md

ckpts/LivePortrait/requirements.txt

ckpts/LivePortrait/requirements_base.txt

ckpts/LivePortrait/requirements_macOS.txt

ckpts/LivePortrait/speed.py

ckpts/LivePortrait/src/config/__init__.py

ckpts/LivePortrait/src/config/argument_config.py

ckpts/LivePortrait/src/config/base_config.py

ckpts/LivePortrait/src/config/crop_config.py

ckpts/LivePortrait/src/config/inference_config.py

ckpts/LivePortrait/src/config/models.yaml

ckpts/LivePortrait/src/gradio_pipeline.py

ckpts/LivePortrait/src/live_portrait_pipeline.py

ckpts/LivePortrait/src/live_portrait_pipeline_animal.py

ckpts/LivePortrait/src/live_portrait_wrapper.py

ckpts/LivePortrait/src/modules/__init__.py

ckpts/LivePortrait/src/modules/appearance_feature_extractor.py

ckpts/LivePortrait/src/modules/convnextv2.py

ckpts/LivePortrait/src/modules/dense_motion.py

ckpts/LivePortrait/src/modules/motion_extractor.py

ckpts/LivePortrait/src/modules/spade_generator.py

ckpts/LivePortrait/src/modules/stitching_retargeting_network.py

ckpts/LivePortrait/src/modules/util.py

ckpts/LivePortrait/src/modules/warping_network.py

ckpts/LivePortrait/src/utils/__init__.py

ckpts/LivePortrait/src/utils/animal_landmark_runner.py

ckpts/LivePortrait/src/utils/camera.py

ckpts/LivePortrait/src/utils/check_windows_port.py

ckpts/LivePortrait/src/utils/crop.py

ckpts/LivePortrait/src/utils/cropper.py

ckpts/LivePortrait/src/utils/dependencies/XPose/config_model/UniPose_SwinT.py

ckpts/LivePortrait/src/utils/dependencies/XPose/config_model/coco_transformer.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/__init__.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/attention.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/backbone.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/deformable_transformer.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/fuse_modules.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/mask_generate.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/functions/__init__.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/functions/ms_deform_attn_func.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/modules/__init__.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/modules/ms_deform_attn.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/modules/ms_deform_attn_key_aware.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/setup.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/cpu/ms_deform_attn_cpu.cpp

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/cpu/ms_deform_attn_cpu.h

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_attn_cuda.cu

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_attn_cuda.h

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_im2col_cuda.cuh

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/ms_deform_attn.h

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/src/vision.cpp

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/ops/test.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/position_encoding.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/swin_transformer.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/transformer_deformable.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/transformer_vanilla.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/unipose.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/UniPose/utils.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/__init__.py

ckpts/LivePortrait/src/utils/dependencies/XPose/models/registry.py

ckpts/LivePortrait/src/utils/dependencies/XPose/predefined_keypoints.py

ckpts/LivePortrait/src/utils/dependencies/XPose/transforms.py

ckpts/LivePortrait/src/utils/dependencies/XPose/util/addict.py

ckpts/LivePortrait/src/utils/dependencies/XPose/util/box_ops.py

ckpts/LivePortrait/src/utils/dependencies/XPose/util/config.py

ckpts/LivePortrait/src/utils/dependencies/XPose/util/keypoint_ops.py

ckpts/LivePortrait/src/utils/dependencies/XPose/util/misc.py

ckpts/LivePortrait/src/utils/dependencies/insightface/__init__.py

ckpts/LivePortrait/src/utils/dependencies/insightface/app/__init__.py

ckpts/LivePortrait/src/utils/dependencies/insightface/app/common.py

ckpts/LivePortrait/src/utils/dependencies/insightface/app/face_analysis.py

ckpts/LivePortrait/src/utils/dependencies/insightface/data/__init__.py

ckpts/LivePortrait/src/utils/dependencies/insightface/data/image.py

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/Tom_Hanks_54745.png

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/mask_black.jpg

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/mask_blue.jpg

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/mask_green.jpg

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/mask_white.jpg

ckpts/LivePortrait/src/utils/dependencies/insightface/data/images/t1.jpg

ckpts/LivePortrait/src/utils/dependencies/insightface/data/objects/meanshape_68.pkl

ckpts/LivePortrait/src/utils/dependencies/insightface/data/pickle_object.py

ckpts/LivePortrait/src/utils/dependencies/insightface/data/rec_builder.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/__init__.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/arcface_onnx.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/attribute.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/inswapper.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/landmark.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/model_store.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/model_zoo.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/retinaface.py

ckpts/LivePortrait/src/utils/dependencies/insightface/model_zoo/scrfd.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/__init__.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/constant.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/download.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/face_align.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/filesystem.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/storage.py

ckpts/LivePortrait/src/utils/dependencies/insightface/utils/transform.py

ckpts/LivePortrait/src/utils/face_analysis_diy.py

ckpts/LivePortrait/src/utils/filter.py

ckpts/LivePortrait/src/utils/helper.py

ckpts/LivePortrait/src/utils/human_landmark_runner.py

ckpts/LivePortrait/src/utils/io.py

ckpts/LivePortrait/src/utils/resources/clip_embedding_68.pkl

ckpts/LivePortrait/src/utils/resources/clip_embedding_9.pkl

ckpts/LivePortrait/src/utils/resources/lip_array.pkl

ckpts/LivePortrait/src/utils/resources/mask_template.png

ckpts/LivePortrait/src/utils/retargeting_utils.py

ckpts/LivePortrait/src/utils/rprint.py

ckpts/LivePortrait/src/utils/timer.py

ckpts/LivePortrait/src/utils/video.py

ckpts/LivePortrait/src/utils/viz.py

ckpts/naturalspeech3_facodec/.gitattributes

ckpts/naturalspeech3_facodec/README.md

ckpts/naturalspeech3_facodec/ns3_facodec_decoder.bin

ckpts/naturalspeech3_facodec/ns3_facodec_decoder_v2.bin

ckpts/naturalspeech3_facodec/ns3_facodec_encoder.bin

ckpts/naturalspeech3_facodec/ns3_facodec_encoder_v2.bin

ckpts/naturalspeech3_facodec/ns3_facodec_redecoder.bin

ckpts/step-92000.safetensors

configs/inference/inference_fusion.yaml

configs/model/dit/audio.json

configs/model/dit/video.json

distributed_comms/__pycache__/communications.cpython-310.pyc

distributed_comms/__pycache__/parallel_states.cpython-310.pyc

distributed_comms/__pycache__/util.cpython-310.pyc

distributed_comms/communications.py

distributed_comms/parallel_states.py

distributed_comms/util.py

download_weights.py

example_prompts/.ipynb_checkpoints/benchmark_example-checkpoint.csv

example_prompts/benchmark/.DS_Store

example_prompts/benchmark/audio/00011_audio.wav

example_prompts/benchmark/audio/00046_audio.wav

example_prompts/benchmark/audio/00069_audio.wav

example_prompts/benchmark/frames/00011_frame.jpg

example_prompts/benchmark/frames/00046_frame.jpg

example_prompts/benchmark/frames/00069_frame.png

example_prompts/benchmark/full_video_prompt/00011_full_caption.txt

example_prompts/benchmark/full_video_prompt/00046_full_caption.txt

example_prompts/benchmark/full_video_prompt/00069_full_caption.txt

example_prompts/benchmark/spoken_content/00011_gt.txt

example_prompts/benchmark/spoken_content/00046_gt.txt

example_prompts/benchmark/spoken_content/00069_gt.txt

example_prompts/benchmark_example.csv

infer.py

inference.sh

modules/__init__.py

modules/__pycache__/__init__.cpython-310.pyc

modules/__pycache__/attention.cpython-310.pyc

modules/__pycache__/fusion.cpython-310.pyc

modules/__pycache__/model.cpython-310.pyc

modules/__pycache__/t5.cpython-310.pyc

modules/__pycache__/tokenizers.cpython-310.pyc

modules/__pycache__/vae2_2.cpython-310.pyc

modules/attention.py

modules/face_cropper/__init__.py

modules/face_cropper/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/__pycache__/base_config.cpython-310.pyc

modules/face_cropper/__pycache__/crop.cpython-310.pyc

modules/face_cropper/__pycache__/crop_config.cpython-310.pyc

modules/face_cropper/__pycache__/cropper.cpython-310.pyc

modules/face_cropper/__pycache__/face_analysis_diy.cpython-310.pyc

modules/face_cropper/__pycache__/human_landmark_runner.cpython-310.pyc

modules/face_cropper/__pycache__/io.cpython-310.pyc

modules/face_cropper/__pycache__/rprint.cpython-310.pyc

modules/face_cropper/__pycache__/timer.cpython-310.pyc

modules/face_cropper/animal_landmark_runner.py

modules/face_cropper/base_config.py

modules/face_cropper/crop.py

modules/face_cropper/crop_config.py

modules/face_cropper/cropper.py

modules/face_cropper/dependencies/XPose/config_model/UniPose_SwinT.py

modules/face_cropper/dependencies/XPose/config_model/coco_transformer.py

modules/face_cropper/dependencies/XPose/models/UniPose/__init__.py

modules/face_cropper/dependencies/XPose/models/UniPose/attention.py

modules/face_cropper/dependencies/XPose/models/UniPose/backbone.py

modules/face_cropper/dependencies/XPose/models/UniPose/deformable_transformer.py

modules/face_cropper/dependencies/XPose/models/UniPose/fuse_modules.py

modules/face_cropper/dependencies/XPose/models/UniPose/mask_generate.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/functions/__init__.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/functions/ms_deform_attn_func.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/modules/__init__.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/modules/ms_deform_attn.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/modules/ms_deform_attn_key_aware.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/setup.py

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/cpu/ms_deform_attn_cpu.cpp

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/cpu/ms_deform_attn_cpu.h

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_attn_cuda.cu

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_attn_cuda.h

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/cuda/ms_deform_im2col_cuda.cuh

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/ms_deform_attn.h

modules/face_cropper/dependencies/XPose/models/UniPose/ops/src/vision.cpp

modules/face_cropper/dependencies/XPose/models/UniPose/ops/test.py

modules/face_cropper/dependencies/XPose/models/UniPose/position_encoding.py

modules/face_cropper/dependencies/XPose/models/UniPose/swin_transformer.py

modules/face_cropper/dependencies/XPose/models/UniPose/transformer_deformable.py

modules/face_cropper/dependencies/XPose/models/UniPose/transformer_vanilla.py

modules/face_cropper/dependencies/XPose/models/UniPose/unipose.py

modules/face_cropper/dependencies/XPose/models/UniPose/utils.py

modules/face_cropper/dependencies/XPose/models/__init__.py

modules/face_cropper/dependencies/XPose/models/registry.py

modules/face_cropper/dependencies/XPose/predefined_keypoints.py

modules/face_cropper/dependencies/XPose/transforms.py

modules/face_cropper/dependencies/XPose/util/addict.py

modules/face_cropper/dependencies/XPose/util/box_ops.py

modules/face_cropper/dependencies/XPose/util/config.py

modules/face_cropper/dependencies/XPose/util/keypoint_ops.py

modules/face_cropper/dependencies/XPose/util/misc.py

modules/face_cropper/dependencies/insightface/__init__.py

modules/face_cropper/dependencies/insightface/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/dependencies/insightface/app/__init__.py

modules/face_cropper/dependencies/insightface/app/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/dependencies/insightface/app/__pycache__/common.cpython-310.pyc

modules/face_cropper/dependencies/insightface/app/__pycache__/face_analysis.cpython-310.pyc

modules/face_cropper/dependencies/insightface/app/common.py

modules/face_cropper/dependencies/insightface/app/face_analysis.py

modules/face_cropper/dependencies/insightface/data/__init__.py

modules/face_cropper/dependencies/insightface/data/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/dependencies/insightface/data/__pycache__/image.cpython-310.pyc

modules/face_cropper/dependencies/insightface/data/__pycache__/pickle_object.cpython-310.pyc

modules/face_cropper/dependencies/insightface/data/image.py

modules/face_cropper/dependencies/insightface/data/images/Tom_Hanks_54745.png

modules/face_cropper/dependencies/insightface/data/images/mask_black.jpg

modules/face_cropper/dependencies/insightface/data/images/mask_blue.jpg

modules/face_cropper/dependencies/insightface/data/images/mask_green.jpg

modules/face_cropper/dependencies/insightface/data/images/mask_white.jpg

modules/face_cropper/dependencies/insightface/data/images/t1.jpg

modules/face_cropper/dependencies/insightface/data/objects/meanshape_68.pkl

modules/face_cropper/dependencies/insightface/data/pickle_object.py

modules/face_cropper/dependencies/insightface/data/rec_builder.py

modules/face_cropper/dependencies/insightface/model_zoo/__init__.py

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/arcface_onnx.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/attribute.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/inswapper.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/landmark.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/model_zoo.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/retinaface.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/__pycache__/scrfd.cpython-310.pyc

modules/face_cropper/dependencies/insightface/model_zoo/arcface_onnx.py

modules/face_cropper/dependencies/insightface/model_zoo/attribute.py

modules/face_cropper/dependencies/insightface/model_zoo/inswapper.py

modules/face_cropper/dependencies/insightface/model_zoo/landmark.py

modules/face_cropper/dependencies/insightface/model_zoo/model_store.py

modules/face_cropper/dependencies/insightface/model_zoo/model_zoo.py

modules/face_cropper/dependencies/insightface/model_zoo/retinaface.py

modules/face_cropper/dependencies/insightface/model_zoo/scrfd.py

modules/face_cropper/dependencies/insightface/utils/__init__.py

modules/face_cropper/dependencies/insightface/utils/__pycache__/__init__.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/constant.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/download.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/face_align.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/filesystem.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/storage.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/__pycache__/transform.cpython-310.pyc

modules/face_cropper/dependencies/insightface/utils/constant.py

modules/face_cropper/dependencies/insightface/utils/download.py

modules/face_cropper/dependencies/insightface/utils/face_align.py

modules/face_cropper/dependencies/insightface/utils/filesystem.py

modules/face_cropper/dependencies/insightface/utils/storage.py

modules/face_cropper/dependencies/insightface/utils/transform.py

modules/face_cropper/face_analysis_diy.py

modules/face_cropper/human_landmark_runner.py

modules/face_cropper/io.py

modules/face_cropper/resources/clip_embedding_68.pkl

modules/face_cropper/resources/clip_embedding_9.pkl

modules/face_cropper/resources/lip_array.pkl

modules/face_cropper/resources/mask_template.png

modules/face_cropper/rprint.py

modules/face_cropper/timer.py

modules/fusion.py

modules/mmaudio/__init__.py

modules/mmaudio/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/__pycache__/features_utils.cpython-310.pyc

modules/mmaudio/ext/__init__.py

modules/mmaudio/ext/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/__pycache__/mel_converter.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__init__.py

modules/mmaudio/ext/autoencoder/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__pycache__/autoencoder.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__pycache__/distributions.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__pycache__/edm2_utils.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__pycache__/vae.cpython-310.pyc

modules/mmaudio/ext/autoencoder/__pycache__/vae_modules.cpython-310.pyc

modules/mmaudio/ext/autoencoder/autoencoder.py

modules/mmaudio/ext/autoencoder/distributions.py

modules/mmaudio/ext/autoencoder/edm2_utils.py

modules/mmaudio/ext/autoencoder/vae.py

modules/mmaudio/ext/autoencoder/vae_modules.py

modules/mmaudio/ext/bigvgan/LICENSE

modules/mmaudio/ext/bigvgan/__init__.py

modules/mmaudio/ext/bigvgan/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/bigvgan/__pycache__/activations.cpython-310.pyc

modules/mmaudio/ext/bigvgan/__pycache__/bigvgan.cpython-310.pyc

modules/mmaudio/ext/bigvgan/__pycache__/models.cpython-310.pyc

modules/mmaudio/ext/bigvgan/__pycache__/utils.cpython-310.pyc

modules/mmaudio/ext/bigvgan/activations.py

modules/mmaudio/ext/bigvgan/alias_free_torch/__init__.py

modules/mmaudio/ext/bigvgan/alias_free_torch/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/bigvgan/alias_free_torch/__pycache__/act.cpython-310.pyc

modules/mmaudio/ext/bigvgan/alias_free_torch/__pycache__/filter.cpython-310.pyc

modules/mmaudio/ext/bigvgan/alias_free_torch/__pycache__/resample.cpython-310.pyc

modules/mmaudio/ext/bigvgan/alias_free_torch/act.py

modules/mmaudio/ext/bigvgan/alias_free_torch/filter.py

modules/mmaudio/ext/bigvgan/alias_free_torch/resample.py

modules/mmaudio/ext/bigvgan/bigvgan.py

modules/mmaudio/ext/bigvgan/bigvgan_vocoder.yml

modules/mmaudio/ext/bigvgan/env.py

modules/mmaudio/ext/bigvgan/incl_licenses/LICENSE_1

modules/mmaudio/ext/bigvgan/incl_licenses/LICENSE_2

modules/mmaudio/ext/bigvgan/incl_licenses/LICENSE_3

modules/mmaudio/ext/bigvgan/incl_licenses/LICENSE_4

modules/mmaudio/ext/bigvgan/incl_licenses/LICENSE_5

modules/mmaudio/ext/bigvgan/models.py

modules/mmaudio/ext/bigvgan/utils.py

modules/mmaudio/ext/bigvgan_v2/LICENSE

modules/mmaudio/ext/bigvgan_v2/__init__.py

modules/mmaudio/ext/bigvgan_v2/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/__pycache__/activations.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/__pycache__/bigvgan.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/__pycache__/env.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/__pycache__/utils.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/activations.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/__init__.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/activation1d.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation.cpp

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/anti_alias_activation_cuda.cu

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/compat.h

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/load.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/cuda/type_shim.h

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__init__.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__pycache__/__init__.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__pycache__/act.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__pycache__/filter.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/__pycache__/resample.cpython-310.pyc

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/act.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/filter.py

modules/mmaudio/ext/bigvgan_v2/alias_free_activation/torch/resample.py

modules/mmaudio/ext/bigvgan_v2/bigvgan.py

modules/mmaudio/ext/bigvgan_v2/env.py

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_1

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_2

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_3

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_4

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_5

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_6

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_7

modules/mmaudio/ext/bigvgan_v2/incl_licenses/LICENSE_8

modules/mmaudio/ext/bigvgan_v2/utils.py

modules/mmaudio/ext/mel_converter.py

modules/mmaudio/ext/rotary_embeddings.py

modules/mmaudio/ext/stft_converter.py

modules/mmaudio/ext/stft_converter_mel.py

modules/mmaudio/features_utils.py

modules/model.py

modules/ns3_codec/README.md

modules/ns3_codec/__init__.py

modules/ns3_codec/__pycache__/__init__.cpython-310.pyc

modules/ns3_codec/__pycache__/facodec.cpython-310.pyc

modules/ns3_codec/__pycache__/gradient_reversal.cpython-310.pyc

modules/ns3_codec/__pycache__/melspec.cpython-310.pyc

modules/ns3_codec/__pycache__/speaker_extractor.cpython-310.pyc

modules/ns3_codec/__pycache__/transformer.cpython-310.pyc

modules/ns3_codec/alias_free_torch/__init__.py

modules/ns3_codec/alias_free_torch/__pycache__/__init__.cpython-310.pyc

modules/ns3_codec/alias_free_torch/__pycache__/act.cpython-310.pyc

modules/ns3_codec/alias_free_torch/__pycache__/filter.cpython-310.pyc

modules/ns3_codec/alias_free_torch/__pycache__/resample.cpython-310.pyc

modules/ns3_codec/alias_free_torch/act.py

modules/ns3_codec/alias_free_torch/filter.py

modules/ns3_codec/alias_free_torch/resample.py

modules/ns3_codec/facodec.py

modules/ns3_codec/gradient_reversal.py

modules/ns3_codec/melspec.py

modules/ns3_codec/quantize/__init__.py

modules/ns3_codec/quantize/__pycache__/__init__.cpython-310.pyc

modules/ns3_codec/quantize/__pycache__/fvq.cpython-310.pyc

modules/ns3_codec/quantize/__pycache__/rvq.cpython-310.pyc

modules/ns3_codec/quantize/fvq.py

modules/ns3_codec/quantize/rvq.py

modules/ns3_codec/speaker_extractor.py

modules/ns3_codec/transformer.py

modules/t5.py

modules/tokenizers.py

modules/vae2_2.py

ovi_fusion_engine.py

requirements.txt

utils/__init__.py

utils/__pycache__/__init__.cpython-310.pyc

utils/__pycache__/fm_solvers.cpython-310.pyc

utils/__pycache__/fm_solvers_unipc.cpython-310.pyc

utils/__pycache__/io_utils.cpython-310.pyc

utils/__pycache__/model_loading_utils.cpython-310.pyc

utils/__pycache__/processing_utils.cpython-310.pyc

utils/__pycache__/utils.cpython-310.pyc

utils/fm_solvers.py

utils/fm_solvers_unipc.py

utils/io_utils.py

utils/model_loading_utils.py

utils/processing_utils.py

utils/utils.py

Related models

More from Omni1307

No other models by this author.

More models

No task type declared.