Today's Image & Video Generation: Fastest-Growing Projects — May 17, 2026
This week, the Image & Video Generation category on GitHub continues to showcase a vibrant ecosystem of innovative projects that cater to both developers and end-users looking for powerful AI-driven solutions. The CookSleep/gpt_image_playground project stands out with its high growth score, indicating significant interest in tools based on OpenAI's gpt-image-2 interface.
CookSleep/gpt_image_playground is an image generation and editing tool built upon the OpenAI gpt-image-2 API, offering a comprehensive suite of features for creative professionals. Its impressive growth score of 62.92 and over 1,300 stars reflect the growing demand for user-friendly platforms that harness advanced AI capabilities.
mrslimslim/gpt-image-canvas is a local professional AI canvas built with tldraw, providing users with an intuitive interface to create and edit images locally. With its steady growth score of 25.63 and 350 stars, it demonstrates the increasing interest in tools that integrate AI functionalities directly into familiar design environments.
helloianneo/ian-handdrawn-ppt generates Chinese hand-drawn technical PPT slides with a focus on full-page image generation for both cover pages and content frames, outputting PNG files. This project's growth score of 24.68 and its popularity (834 stars) indicate the demand for specialized AI tools that cater to specific creative needs in professional settings.
EvoLinkAI/awesome-gpt-image-2-API-and-Prompts is a repository compiling API details and prompts for the GPT-Image-2 model, serving as a valuable resource for developers and enthusiasts. With 14,694 stars and a growth score of 22.43, it highlights the importance of community-driven resources in facilitating the adoption of new AI technologies.
ldige-jun/ima2-gen is a minimal command-line interface (CLI) along with a web UI for generating images using OpenAI's GPT Image 2 model, supporting both paid API key and free OAuth authentication methods. Its growth score of 17.71 and 222 stars suggest the growing interest in flexible tools that cater to various user needs and budgets.
OpenImagingLab/AnyRecon is an innovative project focused on arbitrary-view 3D reconstruction using a video diffusion model, aiming to revolutionize how we perceive and interact with digital environments. Despite its relatively lower growth score of 8.61 and 335 stars, it showcases the potential for advanced AI techniques in emerging areas like 3D modeling.
RareSense/Nova3D is an open-source client for nova3d.xyz that enables part-aware 3D generation from text or reference images, providing a powerful toolset for creating detailed digital assets. With a growth score of 8.36 and 61 stars, it reflects the ongoing interest in tools that bridge the gap between textual inputs and high-fidelity visual outputs.
kevinchin12/ImageLens is a Chrome extension designed to reverse-engineer prompts from web images and validate them via live generation, offering users an efficient way to experiment with AI-generated imagery. Its growth score of 5.34 and 69 stars indicate the increasing demand for tools that simplify the process of working with AI-driven image generation.
jieyefriic/nbcraft is a multi-backend CLI tool supporting various image and video generation services, including Gemini, DashScope, Volcengine Ark, and OpenAI gpt-image-2. With its growth score of 5.18 and 155 stars, it underscores the importance of versatile platforms that can leverage different AI models to meet diverse user requirements.
ailuntx/Thinking-with-Visual-Primitives is an archived snapshot of a project focused on visual primitive thinking in AI-generated imagery, though its limited activity and growth score of 5.06 suggest that interest may be waning compared to other active projects in the space.
CookSleep/gpt_image_playground is an image generation and editing tool built upon the OpenAI gpt-image-2 API, offering a comprehensive suite of features for creative professionals. Its impressive growth score of 62.92 and over 1,300 stars reflect the growing demand for user-friendly platforms that harness advanced AI capabilities.
mrslimslim/gpt-image-canvas is a local professional AI canvas built with tldraw, providing users with an intuitive interface to create and edit images locally. With its steady growth score of 25.63 and 350 stars, it demonstrates the increasing interest in tools that integrate AI functionalities directly into familiar design environments.
helloianneo/ian-handdrawn-ppt generates Chinese hand-drawn technical PPT slides with a focus on full-page image generation for both cover pages and content frames, outputting PNG files. This project's growth score of 24.68 and its popularity (834 stars) indicate the demand for specialized AI tools that cater to specific creative needs in professional settings.
EvoLinkAI/awesome-gpt-image-2-API-and-Prompts is a repository compiling API details and prompts for the GPT-Image-2 model, serving as a valuable resource for developers and enthusiasts. With 14,694 stars and a growth score of 22.43, it highlights the importance of community-driven resources in facilitating the adoption of new AI technologies.
ldige-jun/ima2-gen is a minimal command-line interface (CLI) along with a web UI for generating images using OpenAI's GPT Image 2 model, supporting both paid API key and free OAuth authentication methods. Its growth score of 17.71 and 222 stars suggest the growing interest in flexible tools that cater to various user needs and budgets.
OpenImagingLab/AnyRecon is an innovative project focused on arbitrary-view 3D reconstruction using a video diffusion model, aiming to revolutionize how we perceive and interact with digital environments. Despite its relatively lower growth score of 8.61 and 335 stars, it showcases the potential for advanced AI techniques in emerging areas like 3D modeling.
RareSense/Nova3D is an open-source client for nova3d.xyz that enables part-aware 3D generation from text or reference images, providing a powerful toolset for creating detailed digital assets. With a growth score of 8.36 and 61 stars, it reflects the ongoing interest in tools that bridge the gap between textual inputs and high-fidelity visual outputs.
kevinchin12/ImageLens is a Chrome extension designed to reverse-engineer prompts from web images and validate them via live generation, offering users an efficient way to experiment with AI-generated imagery. Its growth score of 5.34 and 69 stars indicate the increasing demand for tools that simplify the process of working with AI-driven image generation.
jieyefriic/nbcraft is a multi-backend CLI tool supporting various image and video generation services, including Gemini, DashScope, Volcengine Ark, and OpenAI gpt-image-2. With its growth score of 5.18 and 155 stars, it underscores the importance of versatile platforms that can leverage different AI models to meet diverse user requirements.
ailuntx/Thinking-with-Visual-Primitives is an archived snapshot of a project focused on visual primitive thinking in AI-generated imagery, though its limited activity and growth score of 5.06 suggest that interest may be waning compared to other active projects in the space.