mmpose/projects/mmpose4aigc

MMPose for AIGC (AI Generated Content)

English | 简体中文

This project will demonstrate how to use MMPose to generate skeleton images for pose guided AI image generation.

Currently, we support:

• T2I Adapter

Please feel free to share interesting pose-guided AIGC projects to us!

Get Started

Generate OpenPose-style Skeleton

Step 1: Preparation

Run the following commands to prepare the project:

# install mmpose mmdet
pip install openmim
git clone https://github.com/open-mmlab/mmpose.git
cd mmpose
mim install -e .
mim install "mmdet>=3.0.0rc6"

# download models
bash download_models.sh

Step 2: Generate a Skeleton Image

Run the following command to generate a skeleton image:

# generate a skeleton image
bash mmpose_openpose.sh ../../tests/data/coco/000000000785.jpg

The input image and its skeleton are as follows:

Generate MMPose-style Skeleton

Step 1: Preparation

Env Requirements:

• GCC >= 7.5
• cmake >= 3.14

Run the following commands to install the project:

bash install_posetracker_linux.sh

After installation, files are organized as follows:

|----mmdeploy-1.0.0-linux-x86_64-cxx11abi
|    |----README.md
|    |----rtmpose-ort
|    |    |----rtmdet-nano
|    |    |----rtmpose-m
|    |    |----000000147979.jpg
|    |    |----t2i-adapter_skeleton.txt

Step 2: Generate a Skeleton Image

Run the following command to generate a skeleton image:

# generate a skeleton image
bash mmpose_style_skeleton.sh \
    mmdeploy-1.0.0-linux-x86_64-cxx11abi/rtmpose-ort/000000147979.jpg

For more details, you can refer to RTMPose.

The input image and its skeleton are as follows:

Upload to T2I-Adapter

The demo page of T2I- Adapter is Here.

Gallery