feat: update env, doc, one-installer (#283)

* chore: remove transformers for macOS

* chore: specify torch cuda version

* chore: update install instruction

* chore: update install instruction

* chore: update readme

* doc: update

---------

Co-authored-by: zzzweakman <1819489045@qq.com>
This commit is contained in:
Jianzhu Guo
2024-08-05 18:04:26 +08:00
committed by GitHub
parent 357226b2e7
commit 6a7efe2742
6 changed files with 61 additions and 15 deletions

View File

@@ -13,14 +13,14 @@
</table>
🎉 We are excited to announce the release of a new version featuring animals mode, along with several other updates. Special thanks to the dedicated efforts of the LivePortrait team. 💪
🎉 We are excited to announce the release of a new version featuring animals mode, along with several other updates. Special thanks to the dedicated efforts of the LivePortrait team. 💪 We also provided an one-click installer for Windows users, checkout the details [here](./2024-08-05.md).
### Updates on Animals mode
We are pleased to announce the release of the animals mode, which is fine-tuned on approximately 230K frames of various animals (mostly cats and dogs). The trained weights have been updated in the `liveportrait_animals` subdirectory, available on [HuggingFace](https://huggingface.co/KwaiVGI/LivePortrait/tree/main/) or [Google Drive](https://drive.google.com/drive/u/0/folders/1UtKgzKjFAOmZkhNK-OYT0caJ_w2XAnib). You should [download the weights](https://github.com/KwaiVGI/LivePortrait?tab=readme-ov-file#2-download-pretrained-weights) before running. There are two ways to run this mode.
> Please note that we have not trained the stitching and retargeting modules for the animals model due to several technical issues. _This may be addressed in future updates._ Therefore, we recommend **disabling stitching by setting the `--no_flag_stitching`** option when running the model. Additionally, `paste-back` is also not recommended.
Before launching, ensure you have installed `transformers==4.22.0`, `pillow>=10.2.0`, which are already updated in [`requirements_base.txt`](../../../requirements_base.txt). We have chosen [XPose](https://github.com/IDEA-Research/X-Pose) as the keypoints detector for animals. This relies on `transformers` and requires building an OP named `MultiScaleDeformableAttention` by
Before launching, ensure you have installed `transformers==4.22.0`, `pillow>=10.2.0`, which are already updated in [`requirements_base.txt`](../../../requirements_base.txt). We have chosen [X-Pose](https://github.com/IDEA-Research/X-Pose) as the keypoints detector for animals. This relies on `transformers` and requires building an OP named `MultiScaleDeformableAttention` by
```bash
cd src/utils/dependencies/XPose/models/UniPose/ops
python setup.py build install
@@ -38,7 +38,7 @@ python app_animals.py # --server_port 8889 --server_name "0.0.0.0" --share
```
> [!WARNING]
> [XPose](https://github.com/IDEA-Research/X-Pose) is only for Non-commercial Scientific Research Purposes, you should remove and replace it with other detectors if you use it for commercial purposes.
> [X-Pose](https://github.com/IDEA-Research/X-Pose) is only for Non-commercial Scientific Research Purposes, you should remove and replace it with other detectors if you use it for commercial purposes.
### Updates on Humans mode
@@ -50,6 +50,7 @@ python app_animals.py # --server_port 8889 --server_name "0.0.0.0" --share
- [**Poe supports LivePortrait**](https://poe.com/LivePortrait). Check out the news on [X](https://x.com/poe_platform/status/1816136105781256260).
- [ComfyUI-LivePortraitKJ](https://github.com/kijai/ComfyUI-LivePortraitKJ) (1.1K 🌟) now includes MediaPipe as an alternative to InsightFace, ensuring the license remains under MIT and Apache 2.0.
- [ComfyUI-AdvancedLivePortrait](https://github.com/PowerHouseMan/ComfyUI-AdvancedLivePortrait) features real-time portrait pose/expression editing and animation, and is registered with ComfyUI-Manager.