Today's Image & Video Generation: Fastest-Growing Projects — June 18, 2026
Today's the Image & Video Generation space on GitHub, we see a diverse array of projects gaining traction, from sophisticated AI-driven web interfaces for image generation to offline desktop utilities that streamline photo editing tasks. The standout project is `ilab-gpt-conjure`, which has seen significant growth and user engagement due to its comprehensive feature set designed for both beginners and advanced users.
kadevin/ilab-gpt-conjure
This repository offers an AI image generation WebUI workbench tailored for GPT-image-2, providing Codex Responses support and compatibility with the OpenAI API. It features a shared gallery, multi-type quick chips, prompt templates, concurrent task management, and local queue handling.
With a high growth score of 45.65 and over 493 stars, it's clear that developers are drawn to its robust set of tools designed for efficient AI image creation.
techjarves/Local-AI-Image-Generator
A fully self-contained offline AI image generation studio for Windows, this tool runs Stable Diffusion locally without any manual setup. It automatically configures CUDA for Nvidia GPUs and Vulkan for AMD/Intel Arc cards.
Its steady growth score of 22.21 and 208 stars reflect its value in offering a seamless local environment for users who prefer to work offline with zero system-wide dependencies.
Lekien082/AI-Photo-Background-Remover
This desktop utility removes photo backgrounds locally using AI, ensuring high-resolution output without the need for an internet connection.
With 75 stars and a growth score of 15.50, it stands out as a practical solution for those looking to enhance their images quickly and efficiently offline.
nv-tlabs/dvlt
This repository is the official implementation of Déjà View, which uses looping transformers for multi-view 3D reconstruction.
Despite having fewer recent commits (3 in 30 days), its strong growth score of 10.34 and 333 stars indicate that it remains a relevant and interesting project for researchers working on advanced image processing techniques.
helloianneo/ian-xiaohei-scenes
Xiaohei 2.0 Codex Skill is designed to create Chinese real-object article illustrations and long-scroll story images.
With 213 stars and a growth score of 9.86, this tool demonstrates steady interest in its specialized content creation capabilities.
helloianneo/ian-xiaohei-illustrations
This project generates hand-drawn illustrations with red, orange, and blue annotations for Chinese article illustrations.
It has amassed an impressive 5,018 stars and a growth score of 8.40, reflecting the high demand for its unique and visually appealing output.
Guo-chunyu/Chaning.G-s-Lrlab
This workflow integrates large language models with neural network-level color grading algorithms to enhance photography post-processing.
With 100 stars and a moderate growth score of 4.11, it captures the interest of photographers and image editors looking for AI-driven inspiration.
MSALab-PKU/LoomVideo
LoomVideo is an implementation that unifies multimodal inputs into video generation and editing.
Its 62 stars and a growth score of 3.62 indicate its relevance in advancing video creation techniques, albeit with a smaller but dedicated user base.
keshik6/gpic
GPIC provides a giant permissive image corpus for visual generation tasks.
With 44 stars and a growth score of 2.67, it continues to attract users interested in leveraging large-scale image datasets for their projects.
These tools span various aspects of AI-driven image and video creation, from web-based interfaces to offline desktop applications, showcasing the diverse needs and interests within this vibrant community.
kadevin/ilab-gpt-conjure
This repository offers an AI image generation WebUI workbench tailored for GPT-image-2, providing Codex Responses support and compatibility with the OpenAI API. It features a shared gallery, multi-type quick chips, prompt templates, concurrent task management, and local queue handling.
With a high growth score of 45.65 and over 493 stars, it's clear that developers are drawn to its robust set of tools designed for efficient AI image creation.
techjarves/Local-AI-Image-Generator
A fully self-contained offline AI image generation studio for Windows, this tool runs Stable Diffusion locally without any manual setup. It automatically configures CUDA for Nvidia GPUs and Vulkan for AMD/Intel Arc cards.
Its steady growth score of 22.21 and 208 stars reflect its value in offering a seamless local environment for users who prefer to work offline with zero system-wide dependencies.
Lekien082/AI-Photo-Background-Remover
This desktop utility removes photo backgrounds locally using AI, ensuring high-resolution output without the need for an internet connection.
With 75 stars and a growth score of 15.50, it stands out as a practical solution for those looking to enhance their images quickly and efficiently offline.
nv-tlabs/dvlt
This repository is the official implementation of Déjà View, which uses looping transformers for multi-view 3D reconstruction.
Despite having fewer recent commits (3 in 30 days), its strong growth score of 10.34 and 333 stars indicate that it remains a relevant and interesting project for researchers working on advanced image processing techniques.
helloianneo/ian-xiaohei-scenes
Xiaohei 2.0 Codex Skill is designed to create Chinese real-object article illustrations and long-scroll story images.
With 213 stars and a growth score of 9.86, this tool demonstrates steady interest in its specialized content creation capabilities.
helloianneo/ian-xiaohei-illustrations
This project generates hand-drawn illustrations with red, orange, and blue annotations for Chinese article illustrations.
It has amassed an impressive 5,018 stars and a growth score of 8.40, reflecting the high demand for its unique and visually appealing output.
Guo-chunyu/Chaning.G-s-Lrlab
This workflow integrates large language models with neural network-level color grading algorithms to enhance photography post-processing.
With 100 stars and a moderate growth score of 4.11, it captures the interest of photographers and image editors looking for AI-driven inspiration.
MSALab-PKU/LoomVideo
LoomVideo is an implementation that unifies multimodal inputs into video generation and editing.
Its 62 stars and a growth score of 3.62 indicate its relevance in advancing video creation techniques, albeit with a smaller but dedicated user base.
keshik6/gpic
GPIC provides a giant permissive image corpus for visual generation tasks.
With 44 stars and a growth score of 2.67, it continues to attract users interested in leveraging large-scale image datasets for their projects.
These tools span various aspects of AI-driven image and video creation, from web-based interfaces to offline desktop applications, showcasing the diverse needs and interests within this vibrant community.