Today's Image & Video Generation: Fastest-Growing Projects — June 24, 2026
Today's the Image & Video Generation space, we see a continued surge of interest in AI-driven platforms that offer both local and cloud-based solutions for generating high-quality images and videos. Developers are increasingly focusing on user-friendly interfaces and robust backend functionalities to cater to diverse needs ranging from artistic creation to practical applications like photo editing and video production.
kadevin/ilab-gpt-conjure is an AI image generation WebUI workbench that supports GPT-image-2, Codex Responses, and OpenAI-compatible API access. It features a shared gallery, multi-type quick chips, prompt templates, concurrent tasks, and local queue management. With its high growth score of 33.00 and over 570 stars, this project is gaining traction for its comprehensive set of tools that enhance the user experience in generating AI images.
tianjiangqiji/nova-image-studio offers a self-hosted AI image generation workbench with support for custom models and multiple modes, including PWA (Progressive Web App). It includes features like real-time task handling, agent mode, infinite canvas, inverse prompt word generation, and GIF creation. The project's steady growth score of 28.50 and 66 stars reflect its growing popularity among users who appreciate the flexibility and robustness it offers.
techjarves/Portable-Diffusion provides a portable AI image generator for Windows, Linux, and macOS that runs GGUF and Safetensors models offline with GPU/NPU acceleration detection out of the box. With 130 stars and a growth score of 21.81, this tool is appealing to users who need an easy-to-use solution without any setup hassle.
wanshuiyin/ARIS-Movie-Director brings agentic long-horizon visual generation capabilities to the table by transforming fuzzy stories into image-based movies through a cross-model-audited process. The project's focus on advancing multimodal generation with its high growth score of 21.20 and 30 stars highlights its potential in creating more sophisticated video content.
techjarves/Local-AI-Image-Generator is another self-contained, offline AI image generation studio for Windows that runs Stable Diffusion models locally with automatic CUDA configuration for Nvidia GPUs and Vulkan for AMD/Intel cards. With a growth score of 16.82 and 238 stars, it offers users an accessible way to generate images without the need for any manual setup.
helloianneo/ian-xiaohei-scenes provides Xiaohei 2.0 Codex Skills for generating illustrations and long-scroll story images in Chinese real-object articles. Its low growth score of 8.68 but significant star count (269) suggests that while it may not be expanding rapidly, it has a dedicated user base appreciating its specialized functionality.
nv-tlabs/dvlt is the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction, offering advanced capabilities in multi-view reconstruction. With 343 stars and a growth score of 8.06, it appeals to researchers and developers interested in sophisticated image processing techniques.
calesthio/OpenMontage, an ambitious project aiming to turn AI coding assistants into full-fledged video production studios with over 11 pipelines and 49 tools, is still gaining traction but lacks star counts or recent commits as of this week. Its unique approach to agentic video production sets it apart in the space.
helloianneo/ian-xiaohei-illustrations, generating hand-drawn illustrations for Chinese text articles with specific color schemes and annotations, has amassed an impressive 5,879 stars despite a modest growth score of 5.67. This indicates strong community support for its specialized content creation capabilities.
Lastly, Guo-chunyu/Chaning.G-s-Lrlab offers a professional photography post-processing workflow that integrates large language models with neural network-level color grading algorithms to generate Lightroom presets directly from camera RAW folders or photo collections. With 100 stars and a growth score of 3.08, it caters to professionals looking for innovative ways to enhance their image editing processes.
These projects highlight the dynamic landscape of Image & Video Generation tools on GitHub, with developers continuously pushing boundaries in creativity, accessibility, and technical innovation.
kadevin/ilab-gpt-conjure is an AI image generation WebUI workbench that supports GPT-image-2, Codex Responses, and OpenAI-compatible API access. It features a shared gallery, multi-type quick chips, prompt templates, concurrent tasks, and local queue management. With its high growth score of 33.00 and over 570 stars, this project is gaining traction for its comprehensive set of tools that enhance the user experience in generating AI images.
tianjiangqiji/nova-image-studio offers a self-hosted AI image generation workbench with support for custom models and multiple modes, including PWA (Progressive Web App). It includes features like real-time task handling, agent mode, infinite canvas, inverse prompt word generation, and GIF creation. The project's steady growth score of 28.50 and 66 stars reflect its growing popularity among users who appreciate the flexibility and robustness it offers.
techjarves/Portable-Diffusion provides a portable AI image generator for Windows, Linux, and macOS that runs GGUF and Safetensors models offline with GPU/NPU acceleration detection out of the box. With 130 stars and a growth score of 21.81, this tool is appealing to users who need an easy-to-use solution without any setup hassle.
wanshuiyin/ARIS-Movie-Director brings agentic long-horizon visual generation capabilities to the table by transforming fuzzy stories into image-based movies through a cross-model-audited process. The project's focus on advancing multimodal generation with its high growth score of 21.20 and 30 stars highlights its potential in creating more sophisticated video content.
techjarves/Local-AI-Image-Generator is another self-contained, offline AI image generation studio for Windows that runs Stable Diffusion models locally with automatic CUDA configuration for Nvidia GPUs and Vulkan for AMD/Intel cards. With a growth score of 16.82 and 238 stars, it offers users an accessible way to generate images without the need for any manual setup.
helloianneo/ian-xiaohei-scenes provides Xiaohei 2.0 Codex Skills for generating illustrations and long-scroll story images in Chinese real-object articles. Its low growth score of 8.68 but significant star count (269) suggests that while it may not be expanding rapidly, it has a dedicated user base appreciating its specialized functionality.
nv-tlabs/dvlt is the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction, offering advanced capabilities in multi-view reconstruction. With 343 stars and a growth score of 8.06, it appeals to researchers and developers interested in sophisticated image processing techniques.
calesthio/OpenMontage, an ambitious project aiming to turn AI coding assistants into full-fledged video production studios with over 11 pipelines and 49 tools, is still gaining traction but lacks star counts or recent commits as of this week. Its unique approach to agentic video production sets it apart in the space.
helloianneo/ian-xiaohei-illustrations, generating hand-drawn illustrations for Chinese text articles with specific color schemes and annotations, has amassed an impressive 5,879 stars despite a modest growth score of 5.67. This indicates strong community support for its specialized content creation capabilities.
Lastly, Guo-chunyu/Chaning.G-s-Lrlab offers a professional photography post-processing workflow that integrates large language models with neural network-level color grading algorithms to generate Lightroom presets directly from camera RAW folders or photo collections. With 100 stars and a growth score of 3.08, it caters to professionals looking for innovative ways to enhance their image editing processes.
These projects highlight the dynamic landscape of Image & Video Generation tools on GitHub, with developers continuously pushing boundaries in creativity, accessibility, and technical innovation.