Today's Image & Video Generation: Fastest-Growing Projects — June 25, 2026
Today's the Image & Video Generation space, there's a strong push towards user-friendly interfaces and local processing capabilities for AI image generation. Tools like kadevin/ilab-gpt-conjure and techjarves/Portable-Diffusion are leading the charge with their web-based UIs and portable offline functionalities, respectively. These tools cater to developers looking for ease of use and flexibility in working with AI models.
kadevin's ilab-gpt-conjure offers an AI image generation WebUI workbench that supports Codex Responses and OpenAI-compatible API access, providing a robust platform for concurrent tasks and queue management. With its high growth score of 31.32 and over 500 stars on GitHub, it appears to be growing rapidly due to its comprehensive feature set and ease of use, attracting developers seeking powerful yet user-friendly AI image generation solutions.
tianjiangqiji's nova-image-studio is an AI image generation workbench that allows users to host their own models, supports multiple modes including PWA (Progressive Web App) for real-time task management. It has garnered 73 stars and a growth score of 24.88, indicating its growing popularity among those interested in customizing their AI image generation experience with features like Agent mode and infinite canvas support.
techjarves' Portable-Diffusion is a portable local AI image generator that runs Stable Diffusion models offline on Windows, Linux, and macOS without any setup requirements. Its growth score of 20.06 and 142 stars suggest its growing appeal as users look for no-frills solutions to generate images locally using their preferred hardware accelerations.
wanshuiyin's ARIS-Movie-Director is a project focused on agentic, long-horizon visual generation that transforms fuzzy stories into cross-model-audited image-based movies. It has received 31 stars and a growth score of 19.91, likely due to its innovative approach in merging research with practical applications for both image and video generation.
inlineresearch's Inline-Studio is designed to create visual art using moodboards, powered by ComfyUI. With 99 stars and a growth score of 18.64, it seems to be growing as artists look for creative tools that leverage AI to enhance their workflow through moodboard-driven design.
techjarves' Local-AI-Image-Generator provides a fully self-contained offline studio for Windows users to generate images locally with Stable Diffusion models without manual setup or system-wide dependencies. Its growth score of 16.07 and 240 stars indicate its growing popularity among those who want an easy-to-use, no-setup AI image generation tool that works seamlessly on their local machine.
helloianneo's ian-xiaohei-scenes is a Codex Skill for generating Chinese real-object article illustrations and long-scroll story images with Xiaohei 2.0. With 276 stars and a growth score of 8.71, it appears to be growing as a specialized solution catering to the specific needs of creating visual content in the Chinese context.
nv-tlabs' dvlt is the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction. Despite having more stars than most entries at 345, its lower growth score of 7.79 might indicate that it has reached a stable user base rather than rapid growth.
calesthio's OpenMontage is an agentic video production system with pipelines and tools designed to turn AI coding assistants into full-fledged video production studios. Although the number of stars isn't specified, its low growth score of 6.40 might suggest it's still finding its footing in a highly competitive space.
helloianneo's ian-xiaohei-illustrations is another Codex Skill aimed at generating illustrations for Chinese content with specific visual characteristics and style preferences. With an impressive 6,002 stars and a growth score of 5.75, it indicates strong community interest but might not be growing as rapidly due to its specialized nature.
Today's roundup showcases the diversity in approaches within image and video generation tools, from comprehensive workbenches like ilab-gpt-conjure to highly specialized solutions such as ian-xiaohei-scenes, catering to a wide range of user needs.
kadevin's ilab-gpt-conjure offers an AI image generation WebUI workbench that supports Codex Responses and OpenAI-compatible API access, providing a robust platform for concurrent tasks and queue management. With its high growth score of 31.32 and over 500 stars on GitHub, it appears to be growing rapidly due to its comprehensive feature set and ease of use, attracting developers seeking powerful yet user-friendly AI image generation solutions.
tianjiangqiji's nova-image-studio is an AI image generation workbench that allows users to host their own models, supports multiple modes including PWA (Progressive Web App) for real-time task management. It has garnered 73 stars and a growth score of 24.88, indicating its growing popularity among those interested in customizing their AI image generation experience with features like Agent mode and infinite canvas support.
techjarves' Portable-Diffusion is a portable local AI image generator that runs Stable Diffusion models offline on Windows, Linux, and macOS without any setup requirements. Its growth score of 20.06 and 142 stars suggest its growing appeal as users look for no-frills solutions to generate images locally using their preferred hardware accelerations.
wanshuiyin's ARIS-Movie-Director is a project focused on agentic, long-horizon visual generation that transforms fuzzy stories into cross-model-audited image-based movies. It has received 31 stars and a growth score of 19.91, likely due to its innovative approach in merging research with practical applications for both image and video generation.
inlineresearch's Inline-Studio is designed to create visual art using moodboards, powered by ComfyUI. With 99 stars and a growth score of 18.64, it seems to be growing as artists look for creative tools that leverage AI to enhance their workflow through moodboard-driven design.
techjarves' Local-AI-Image-Generator provides a fully self-contained offline studio for Windows users to generate images locally with Stable Diffusion models without manual setup or system-wide dependencies. Its growth score of 16.07 and 240 stars indicate its growing popularity among those who want an easy-to-use, no-setup AI image generation tool that works seamlessly on their local machine.
helloianneo's ian-xiaohei-scenes is a Codex Skill for generating Chinese real-object article illustrations and long-scroll story images with Xiaohei 2.0. With 276 stars and a growth score of 8.71, it appears to be growing as a specialized solution catering to the specific needs of creating visual content in the Chinese context.
nv-tlabs' dvlt is the official implementation of Déjà View: Looping Transformers for Multi-View 3D Reconstruction. Despite having more stars than most entries at 345, its lower growth score of 7.79 might indicate that it has reached a stable user base rather than rapid growth.
calesthio's OpenMontage is an agentic video production system with pipelines and tools designed to turn AI coding assistants into full-fledged video production studios. Although the number of stars isn't specified, its low growth score of 6.40 might suggest it's still finding its footing in a highly competitive space.
helloianneo's ian-xiaohei-illustrations is another Codex Skill aimed at generating illustrations for Chinese content with specific visual characteristics and style preferences. With an impressive 6,002 stars and a growth score of 5.75, it indicates strong community interest but might not be growing as rapidly due to its specialized nature.
Today's roundup showcases the diversity in approaches within image and video generation tools, from comprehensive workbenches like ilab-gpt-conjure to highly specialized solutions such as ian-xiaohei-scenes, catering to a wide range of user needs.