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
769 forks
Language: Jupyter Notebook
last commit: almost 2 years ago

Related projects:

RepositoryDescriptionStars
bmaltais/photomakerCustomizes realistic human photos using stacked ID embedding.92
fluidgroup/brightroomAn image editing framework using Core Image and Metal for iOS development3,383
ailab-cvc/videocrafterA toolbox for generating and editing video content using diffusion models4,606
zhkkke/modnetA real-time portrait image matting solution in Python3,865
tothebeginning/pulidA deep learning framework for creating customizable images through contrastive alignment and prompt-following.2,795
tencentarc/gfpganAn algorithm for restoring damaged or obscured faces in images36,009
hyperoslo/imagepickerAn iOS image picker solution that allows users to select images from the library and take pictures.4,872
sixlabors/imagesharpA 2D graphics library for .NET that simplifies image processing with a powerful yet simple API.7,495
clovaai/stargan-v2A Python implementation of an image-to-image translation model for generating diverse images across multiple domains.3,513
kwai-kolors/kolorsA Python framework for training and deploying photorealistic text-to-image synthesis models.4,006
open-mmlab/mmagicA toolkit for building and experimenting with generative AI models for image and video generation, restoration, enhancement, and other tasks.6,986
doubiiu/dynamicrafterThis project generates animated videos from open-domain images by leveraging pre-trained video diffusion priors.2,668
skalskip/make-senseAn online tool for labeling photos using computer vision and deep learning techniques3,195
photoprism/photoprismAn AI-powered photo management application built from scratch to organize and tag personal photos without compromising user privacy or functionality.35,805
facebookresearch/imagebindAn AI framework that combines data from multiple sources into a single embedding space, enabling various applications such as cross-modal retrieval and generation.8,424