Today's Image & Video Generation: Fastest-Growing Projects — June 22, 2026
This week, the Image & Video Generation space continues to heat up as developers push the boundaries of what’s possible with AI-powered tools. One notable trend is a surge in demand for user-friendly interfaces that integrate seamlessly with existing workflows and provide robust features such as API compatibility and local queue management.
*kadevin/ilab-gpt-conjure* offers an AI image generation WebUI workbench tailored for GPT-image-2, supporting Codex Responses and OpenAI-compatible APIs. Its growth score of 37.04 reflects its strong community engagement, with over 551 stars indicating significant interest in its comprehensive feature set.
*lcy362/agnes-video-generator* is a free AI video generation tool powered by Agnes AI that enables users to input text ideas and automatically generate multi-scene videos through a web interface. With a growth score of 35.20, it has garnered attention for its ease-of-use and innovative approach to content creation.
*wanshuiyin/ARIS-Movie-Director* aims to bring agentic long-horizon visual generation from concept to reality, transforming fuzzy stories into cross-model-audited image-based movies. This project's growth score of 24.15 highlights its potential for developing advanced multimodal generation capabilities.
*techjarves/Portable-Diffusion* provides a portable Local AI Image Generator and Stable Diffusion GUI that supports GGUF & Safetensors models offline with auto-detected GPU/NPU acceleration. Its growth score of 22.67 reflects increasing interest in its versatile platform compatibility across Windows, Linux, and macOS.
*techjarves/Local-AI-Image-Generator* offers a fully self-contained, offline AI image generation studio for Windows that runs Stable Diffusion locally with zero manual setup and automatic GPU detection. With a growth score of 18.31 and 224 stars, it stands out for its ease of use and extensive model support.
*helloianneo/ian-xiaohei-scenes* is a Codex Skill designed to generate Chinese real-object article illustrations and long-scroll story images, leveraging Xiaohei 2.0 technology. Its growth score of 9.00 suggests steady interest among users seeking specialized content creation tools for specific use cases.
*nv-tlabs/dvlt* presents the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction. With a growth score of 8.63 and 337 stars, it highlights advancements in AI-driven multi-view reconstruction techniques.
*helloianneo/ian-xiaohei-illustrations* offers a Codex Skill for generating 16:9 white-background hand-drawn illustrations with minimal red, orange, and blue annotations for Chinese content. Its growth score of 5.44 indicates sustained interest from users looking to enhance their digital storytelling capabilities.
*calesthio/OpenMontage*, the world's first open-source agentic video production system, integrates various pipelines and tools into a single cohesive platform that can transform an AI coding assistant into a full-fledged video production studio. Despite having no star ratings due to its recent launch, its growth score of 4.90 suggests it is gaining traction for its innovative approach.
*Guo-chunyu/Chaning.G-s-Lrlab* provides a professional photography post-processing workflow that merges the aesthetic characteristics of large language models with neural network-level color grading algorithms, enabling direct AI inspiration integration and one-click Lightroom `.XMP` preset generation. With a growth score of 3.36 and over 100 stars, it demonstrates potential in niche markets for advanced photo editing solutions.
Today's review highlights the diverse range of projects pushing the envelope in image and video generation, from user-friendly interfaces to specialized tools targeting specific creative needs.
*kadevin/ilab-gpt-conjure* offers an AI image generation WebUI workbench tailored for GPT-image-2, supporting Codex Responses and OpenAI-compatible APIs. Its growth score of 37.04 reflects its strong community engagement, with over 551 stars indicating significant interest in its comprehensive feature set.
*lcy362/agnes-video-generator* is a free AI video generation tool powered by Agnes AI that enables users to input text ideas and automatically generate multi-scene videos through a web interface. With a growth score of 35.20, it has garnered attention for its ease-of-use and innovative approach to content creation.
*wanshuiyin/ARIS-Movie-Director* aims to bring agentic long-horizon visual generation from concept to reality, transforming fuzzy stories into cross-model-audited image-based movies. This project's growth score of 24.15 highlights its potential for developing advanced multimodal generation capabilities.
*techjarves/Portable-Diffusion* provides a portable Local AI Image Generator and Stable Diffusion GUI that supports GGUF & Safetensors models offline with auto-detected GPU/NPU acceleration. Its growth score of 22.67 reflects increasing interest in its versatile platform compatibility across Windows, Linux, and macOS.
*techjarves/Local-AI-Image-Generator* offers a fully self-contained, offline AI image generation studio for Windows that runs Stable Diffusion locally with zero manual setup and automatic GPU detection. With a growth score of 18.31 and 224 stars, it stands out for its ease of use and extensive model support.
*helloianneo/ian-xiaohei-scenes* is a Codex Skill designed to generate Chinese real-object article illustrations and long-scroll story images, leveraging Xiaohei 2.0 technology. Its growth score of 9.00 suggests steady interest among users seeking specialized content creation tools for specific use cases.
*nv-tlabs/dvlt* presents the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction. With a growth score of 8.63 and 337 stars, it highlights advancements in AI-driven multi-view reconstruction techniques.
*helloianneo/ian-xiaohei-illustrations* offers a Codex Skill for generating 16:9 white-background hand-drawn illustrations with minimal red, orange, and blue annotations for Chinese content. Its growth score of 5.44 indicates sustained interest from users looking to enhance their digital storytelling capabilities.
*calesthio/OpenMontage*, the world's first open-source agentic video production system, integrates various pipelines and tools into a single cohesive platform that can transform an AI coding assistant into a full-fledged video production studio. Despite having no star ratings due to its recent launch, its growth score of 4.90 suggests it is gaining traction for its innovative approach.
*Guo-chunyu/Chaning.G-s-Lrlab* provides a professional photography post-processing workflow that merges the aesthetic characteristics of large language models with neural network-level color grading algorithms, enabling direct AI inspiration integration and one-click Lightroom `.XMP` preset generation. With a growth score of 3.36 and over 100 stars, it demonstrates potential in niche markets for advanced photo editing solutions.
Today's review highlights the diverse range of projects pushing the envelope in image and video generation, from user-friendly interfaces to specialized tools targeting specific creative needs.