Kolors-IP-Adapter-Plus weights and inference code
π Introduction
We provide IP-Adapter-Plus weights and inference code based on Kolors-Basemodel. Examples of Kolors-IP-Adapter-Plus results are as follows:
Our improvements
- A stronger image feature extractor. We employ the Openai-CLIP-336 model as the image encoder, which allows us to preserve more details in the reference images
- More diverse and high-quality training data: We construct a large-scale and high-quality training dataset inspired by the data strategies of other works. We believe that paired training data can effectively improve performance.
π Evaluation
For evaluation, we create a test set consisting of over 200 reference images and text prompts. We invite several image experts to provide fair ratings for the generated results of different models. The experts rate the generated images based on four criteria: visual appeal, text faithfulness, image faithfulness, and overall satisfaction. Image faithfulness measures the semantic preservation ability of IP-Adapter on reference images, while the other criteria follow the evaluation standards of BaseModel. The specific results are summarized in the table below, where Kolors-IP-Adapter-Plus achieves the highest overall satisfaction score.
Model | Average Overall Satisfaction | Average Image Faithfulness | Average Visual Appeal | Average Text Faithfulness |
---|---|---|---|---|
SDXL-IP-Adapter-Plus | 2.29 | 2.64 | 3.22 | 4.02 |
Midjourney-v6-CW | 2.79 | 3.0 | 3.92 | 4.35 |
Kolors-IP-Adapter-Plus | 3.04 | 3.25 | 4.45 | 4.30 |
The ip_scale parameter is set to 0.3 in SDXL-IP-Adapter-Plus, while Midjourney-v6-CW utilizes the default cw scale.
![](/Kwai-Kolors/Kolors-IP-Adapter-Plus/resolve/main/compare_demo.png)
Kolors-IP-Adapter-Plus employs chinese prompts, while other methods use english prompts.
π οΈ Usage
Requirements
The dependencies and installation are basically the same as the Kolors-BaseModel.
- Repository Cloning and Dependency Installation
apt-get install git-lfs
git clone https://github.com/Kwai-Kolors/Kolors
cd Kolors
conda create --name kolors python=3.8
conda activate kolors
pip install -r requirements.txt
python3 setup.py install
- Weights download linkοΌ
huggingface-cli download --resume-download Kwai-Kolors/Kolors-IP-Adapter-Plus --local-dir weights/Kolors-IP-Adapter-Plus
or
git lfs clone https://huggingface.co/Kwai-Kolors/Kolors-IP-Adapter-Plus weights/Kolors-IP-Adapter-Plus
- InferenceοΌ
python ipadapter/sample_ipadapter_plus.py ./ipadapter/https://raw.githubusercontent.com/junqiangwu/Kolors/master/ipadapter/asset/test_ip.jpg "η©Ώηι»θ²Tζ€θ‘«οΌδΈι’δΈζη»Ώθ²ε€§εεηβε―εΎβ"
python ipadapter/sample_ipadapter_plus.py ./ipadapter/https://raw.githubusercontent.com/junqiangwu/Kolors/master/ipadapter/asset/test_ip2.png "δΈεͺε―η±ηε°ηε¨ε₯θ·"
# The image will be saved to "scripts/outputs/"
Note
The IP-Adapter-FaceID model based on Kolors will also be released soon!
Acknowledgments
- Thanks to IP-Adapter for providing the codebase.
- Downloads last month
- 10,173