PhotoMaker

Photo generator

A tool for generating realistic human photos by customizing existing images using complex algorithms and machine learning models.

PhotoMaker [CVPR 2024]

GitHub

10k stars
102 watching
767 forks
Language: Jupyter Notebook
last commit: 21 days ago

Related projects:

Repository Description Stars
bmaltais/photomaker Customizes realistic human photos using stacked ID embedding. 92
fluidgroup/brightroom An image editing framework using Core Image and Metal for iOS development 3,353
ailab-cvc/videocrafter A toolbox for generating and editing video content using diffusion models 4,561
zhkkke/modnet A real-time portrait image matting solution in Python 3,819
tothebeginning/pulid An AI model for generating images with customized identities and naturalness. 2,619
tencentarc/gfpgan An algorithm for restoring damaged or obscured faces in images 35,898
hyperoslo/imagepicker An iOS image picker solution that allows users to select images from the library and take pictures. 4,868
sixlabors/imagesharp A 2D graphics library for .NET that simplifies image processing with a powerful yet simple API. 7,448
clovaai/stargan-v2 A Python implementation of an image-to-image translation model for generating diverse images across multiple domains. 3,500
kwai-kolors/kolors A Python framework for training and deploying photorealistic text-to-image synthesis models. 3,862
open-mmlab/mmagic A toolkit for building and experimenting with generative AI models for image and video generation, restoration, enhancement, and other tasks. 6,945
doubiiu/dynamicrafter This project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors. 2,580
skalskip/make-sense An online tool for labeling photos using computer vision and deep learning techniques 3,168
photoprism/photoprism An AI-powered photo management application built from scratch to organize and tag personal photos without compromising user privacy or functionality. 35,439
facebookresearch/imagebind An AI framework that combines data from multiple sources into a single embedding space, enabling various applications such as cross-modal retrieval and generation. 8,362