Today's Image & Video Generation: Fastest-Growing Projects — May 18, 2026
Today's the Image & Video Generation space on GitHub, we see a continued surge in interest around AI-driven image editing and generation tools that leverage both cloud-based APIs and open-source frameworks. The CookSleep/gpt_image_playground repository stands out with its high growth score and extensive development activity, reflecting growing demand for interactive image generation solutions.
The CookSleep/gpt_image_playground project is an interface built on top of the OpenAI gpt-image-2 API that allows users to generate and edit images interactively. Its impressive Growth Score of 61.88 and a strong user base of over 1,300 stars indicate significant interest in this type of interactive, cloud-based image generation tool.
Mrslimslim's gpt-image-canvas is another noteworthy project that offers a local AI canvas for professional use built with tldraw. With its Growth Score of 24.80 and nearly 400 stars, it suggests an active community engaged in exploring advanced image editing capabilities on their local machines.
Helloianneo’s ian-handdrawn-ppt is designed to generate hand-drawn style PPT images tailored for presentations and covers both cover pages and body content with PNG output. This project has garnered over 800 stars, highlighting the demand for aesthetically pleasing presentation designs that can be quickly generated using AI.
Lidge-jun's ima2-gen provides a minimal command-line interface (CLI) as well as a web UI to generate images through OpenAI GPT Image 2, supporting dual authentication methods and various generation modes. With a Growth Score of 17.48 and over 200 stars, it demonstrates the need for flexible image generation tools that cater to both free and paid user segments.
AITOOLS101's ai-image-prompt-cookbook offers a collection of AI image prompt words in Chinese, covering diverse use cases such as fashion, children’s wear, product photography, and more. Although its Growth Score is relatively low at 9.50 with only 21 stars, it still serves an essential role by providing curated prompts to help users create specific types of images.
RareSense's Nova3D enables editable, part-aware 3D generation from text or reference images, offering a client for nova3d.xyz. With a Growth Score of 8.67 and over 50 stars, it reflects the growing interest in AI-driven 3D modeling tools that offer detailed control.
OpenImagingLab's AnyRecon is an innovative tool focused on arbitrary-view 3D reconstruction using video diffusion models. It has a Growth Score of 8.33 with 336 stars, indicating strong community support for advanced image and video processing techniques in research and development settings.
BasZ4ll’s Stable-Diffusion-WebUI project provides comprehensive guides and tools to set up the Stable Diffusion web UI, including optimizations for low VRAM systems and extensions like ComfyUI. With a Growth Score of 8.32 and over 200 stars, it demonstrates the community's demand for user-friendly interfaces to complex AI models.
Kevinchin12’s ImageLens is a Chrome extension aimed at reverse-engineering image prompts from web images and validating them instantly through live generation. Its relatively low Growth Score of 5.21 but consistent development (31 commits in 30 days) suggests ongoing refinement for niche use cases requiring rapid prompt testing.
Jieyefriic's nbcraft is a multi-backend CLI tool for image and video generation, supporting multiple APIs including Gemini, DashScope, Volcengine Ark, and OpenAI gpt-image-2. With a Growth Score of 4.86 and nearly 150 stars, it caters to developers looking for flexibility across different AI services.
These projects collectively showcase the dynamic landscape of image and video generation tools on GitHub, with varied approaches catering to both professional and hobbyist users seeking innovative ways to create content using AI technology.
The CookSleep/gpt_image_playground project is an interface built on top of the OpenAI gpt-image-2 API that allows users to generate and edit images interactively. Its impressive Growth Score of 61.88 and a strong user base of over 1,300 stars indicate significant interest in this type of interactive, cloud-based image generation tool.
Mrslimslim's gpt-image-canvas is another noteworthy project that offers a local AI canvas for professional use built with tldraw. With its Growth Score of 24.80 and nearly 400 stars, it suggests an active community engaged in exploring advanced image editing capabilities on their local machines.
Helloianneo’s ian-handdrawn-ppt is designed to generate hand-drawn style PPT images tailored for presentations and covers both cover pages and body content with PNG output. This project has garnered over 800 stars, highlighting the demand for aesthetically pleasing presentation designs that can be quickly generated using AI.
Lidge-jun's ima2-gen provides a minimal command-line interface (CLI) as well as a web UI to generate images through OpenAI GPT Image 2, supporting dual authentication methods and various generation modes. With a Growth Score of 17.48 and over 200 stars, it demonstrates the need for flexible image generation tools that cater to both free and paid user segments.
AITOOLS101's ai-image-prompt-cookbook offers a collection of AI image prompt words in Chinese, covering diverse use cases such as fashion, children’s wear, product photography, and more. Although its Growth Score is relatively low at 9.50 with only 21 stars, it still serves an essential role by providing curated prompts to help users create specific types of images.
RareSense's Nova3D enables editable, part-aware 3D generation from text or reference images, offering a client for nova3d.xyz. With a Growth Score of 8.67 and over 50 stars, it reflects the growing interest in AI-driven 3D modeling tools that offer detailed control.
OpenImagingLab's AnyRecon is an innovative tool focused on arbitrary-view 3D reconstruction using video diffusion models. It has a Growth Score of 8.33 with 336 stars, indicating strong community support for advanced image and video processing techniques in research and development settings.
BasZ4ll’s Stable-Diffusion-WebUI project provides comprehensive guides and tools to set up the Stable Diffusion web UI, including optimizations for low VRAM systems and extensions like ComfyUI. With a Growth Score of 8.32 and over 200 stars, it demonstrates the community's demand for user-friendly interfaces to complex AI models.
Kevinchin12’s ImageLens is a Chrome extension aimed at reverse-engineering image prompts from web images and validating them instantly through live generation. Its relatively low Growth Score of 5.21 but consistent development (31 commits in 30 days) suggests ongoing refinement for niche use cases requiring rapid prompt testing.
Jieyefriic's nbcraft is a multi-backend CLI tool for image and video generation, supporting multiple APIs including Gemini, DashScope, Volcengine Ark, and OpenAI gpt-image-2. With a Growth Score of 4.86 and nearly 150 stars, it caters to developers looking for flexibility across different AI services.
These projects collectively showcase the dynamic landscape of image and video generation tools on GitHub, with varied approaches catering to both professional and hobbyist users seeking innovative ways to create content using AI technology.