Source code for the SIGGRAPH 2024 paper "X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention"
bytedance/X-Portrait 排名第 17,407，有 541 个星标。
同类别比较
bytedance/X-Portrait 排名第 17,407，此处有 8 个同类条目；google-deepmind/dsprites-dataset 排名第 17,408。
同类别比较| 名称 | 排名 | 指标 |
|---|
| LarryJane491/Lora-Training-in-Comfy | 17,399 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 78
- 简介:
- This custom node lets you train LoRA directly in ComfyUI!
|
|---|
| M-Nauta/TCDF | 17,400 | - 语言:
- Jupyter Notebook
- 星标数:
- 541
- 分叉数:
- 119
- 简介:
- Temporal Causal Discovery Framework (PyTorch): discovering causal relationships between time series
|
|---|
| PKU-YuanGroup/Machine-Mindset | 17,402 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 27
- 简介:
- An MBTI Exploration of Large Language Models
|
|---|
| akanimax/pro_gan_pytorch | 17,405 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 95
- 简介:
- Unofficial PyTorch implementation of the paper titled "Progressive growing of GANs for improved Quality, Stability, and Variation"
|
|---|
| google-deepmind/dsprites-dataset | 17,408 | - 语言:
- Jupyter Notebook
- 星标数:
- 541
- 分叉数:
- 69
- 简介:
- Dataset to assess the disentanglement properties of unsupervised learning methods
|
|---|
| hendrycks/apps | 17,410 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 71
- 简介:
- APPS: Automated Programming Progress Standard (NeurIPS 2021)
|
|---|
| hthuwal/sign-language-gesture-recognition | 17,411 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 146
- 简介:
- Sign Language Gesture Recognition From Video Sequences Using RNN And CNN
|
|---|
| lucidrains/iTransformer | 17,412 | - 语言:
- Python
- 星标数:
- 541
- 分叉数:
- 38
- 简介:
- Unofficial implementation of iTransformer - SOTA Time Series Forecasting using Attention networks, out of Tsinghua / Ant group
|
|---|
关键参数与规格
关键参数与规格| 参数 | 值 |
|---|
| 语言 | Python |
|---|
| 类别 | Model Development |
|---|
| 子类别 | Architecture |
|---|
| 关键词 | Video production |
|---|
| 星标数 | 541 |
|---|
| 分叉数 | 50 |
|---|
| 贡献者 | 1 |
|---|
| 创建日期 | 2024-07-18 |
|---|
| 更新日期 | 2026-08-28 |
|---|
| 1 天星标数 | 0 |
|---|
| 7 天星标数 | 0 |
|---|
| 排名 | 17,407 |
|---|
| 上次排名 | 17,190 |
|---|
| 排名变化 | -217 |
|---|
| 7 天星标排名 | 16,086 |
|---|
| 上次 7 天星标排名 | 16,093 |
|---|
| 7 天星标排名变化 | 7 |
|---|
| 总星标排名 | 18,211 |
|---|
| 上次总星标排名 | 18,187 |
|---|
| 总星标排名变化 | -24 |
|---|
| 国家 | China |
|---|
README 摘录
X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention This repository contains the video generation code of SIGGRAPH 2024 paper X-Portrait. Model Please download pre-trained model from here, and save it under "checkpoint/" Testing parameters: **model_config**: config file of the corresponding model **output_dir**: output path for generated video **source_image**: path of source image **driving_video**: path of driving video **best_frame**: specify the frame index in the driving video where the head pose best matches
the source image (note: precision of best_frame index might affect the final quality) **out_frames**: number of generation frames **num_mix**: number of overlapping frames when applying prompt travelling during inference **ddim_steps**: number of inference steps (e. , 30 steps for ddim) Performance Boost **efficiency**: Our model is compatible with LCM LoRA ( which helps reduce the number of inference steps. **expressiveness**: Expressiveness of the results could be boosted if results of other face reenactment approaches, e. 🎓 Citation If you
find this codebase useful for your research, please use the following entry.
常见问题
记录了多少星标和分叉？
bytedance/X-Portrait 有 541 个星标和 50 个分叉。
仓库排名是多少？
bytedance/X-Portrait 排名第 17,407。
记录的语言和类别是什么？
bytedance/X-Portrait 有 541 个星标，语言为 Python，类别为 Model Development。
哪个仓库排名最接近？
bytedance/X-Portrait 与 google-deepmind/dsprites-dataset 比较，后者排名第 17,408，有 541 个星标。
X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention
[You Xie](https://scholar.google.com/citations?user=FV0eXhQAAAAJ&hl=en),
[Hongyi Xu](https://hongyixu37.github.io/homepage/),
[Guoxian Song](https://guoxiansong.github.io/homepage/index.html),
[Chao Wang](https://chaowang.info/),
[Yichun Shi](https://seasonsh.github.io/),
[Linjie Luo](http://linjieluo.com/)
ByteDance Inc.
[](https://arxiv.org/abs/2403.15931)
[](https://byteaigc.github.io/x-portrait/)
[)](https://youtu.be/VGxt5XghRdw)
This repository contains the video generation code of SIGGRAPH 2024 paper X-Portrait.
Installation
Note: Python 3.9 and Cuda 11.8 are required.
bash env_install.sh
Model
Please download pre-trained model from here, and save it under "checkpoint/"
Testing
bash scripts/test_xportrait.sh
parameters:
model_config: config file of the corresponding model
output_dir: output path for generated video
source_image: path of source image
driving_video: path of driving video
best_frame: specify the frame index in the driving video where the head pose best matches the source image (note: precision of best_frame index might affect the final quality)
out_frames: number of generation frames
num_mix: number of overlapping frames when applying prompt travelling during inference
ddim_steps: number of inference steps (e.g., 30 steps for ddim)
Performance Boost
efficiency: Our model is compatible with LCM LoRA (https://huggingface.co/latent-consistency/lcm-lora-sdv1-5), which helps reduce the number of inference steps.
expressiveness: Expressiveness of the results could be boosted if results of other face reenactment approaches, e.g., face vid2vid, could be provided via parameter "--initial_facevid2vid_results".
🎓 Citation
If you find this codebase useful for your research, please use the following entry.
@inproceedings{xie2024x,
title={X-Portrait: Expressive Portrait Animation with Hierarchical Motion Attention},
author={Xie, You and Xu, Hongyi and Song, Guoxian and Wang, Chao and Shi, Yichun and Luo, Linjie},
journal={arXiv preprint arXiv:2403.15931},
year={2024}
}