EasyPhoto_云技派,专注ai人工智能! 121

EasyPhoto is a Webui UI plugin used to generate ai portrait paintings. The code can be used to train a digital avatar related to you. It is recommended to use 5 to 20 portrait pictures for training, preferably half-body photos and without glasses (a small amount is acceptable). After training is complete, we can generate images in the inference section. We support inference using preset template images as well as uploading your own images.

Highlights

EasyPhoto is a Webui UI plugin that can generate AI portraits, used to train digital avatars related to users.

EasyPhoto now supports multi-person generation and training and inference with different base models.

EasyPhoto can run on Windows and Linux systems, requiring approximately 60GB of hard drive space for saving weights and dataset processing.

The EasyPhoto plugin can be installed from GitHub and will also support installation from Available in the future.

The usage of EasyPhoto includes model training and inference. Users can upload 5 to 20 photos for training, and the inference section can choose single-person or multi-person mode.

The algorithm of EasyPhoto includes three parts: architecture overview, training details, and inference details. It mainly generates personalized portrait images through the Stable Diffusion model and the Lora model.