PullRepo

Daily radar for the fastest-growing AI tools & repos

Today's Image & Video Generation: Fastest-Growing Projects — July 18, 2026

Today's the Image & Video Generation space on GitHub, we see a diverse range of projects gaining traction, from AI-driven image enhancement and photo compositing to innovative approaches to video reconstruction and prediction. Notably, several repositories are leveraging machine learning algorithms to enhance user experience by offering real-time previews and batch processing capabilities.

Finderchangchang's codex-autoskin is an agent-native skin engine for the Codex desktop app that allows users to reskin their interface simply by sending one image. With a growth score of 59.25 and 84 stars, this project appears to be growing due to its unique approach to personalizing user interfaces through AI-driven technology.

Photoshop-ai-smart-enhance, developed by FuelMagistrateLead, is an extension for Adobe Photoshop CC that uses machine learning algorithms to enhance images with features like intelligent exposure correction and noise reduction. This repository has a growth score of 47.17 and 108 stars, likely due to its practical application in image enhancement tools widely used by photographers and designers.

Sapphire-PS-AI-Compositor, created by raghurajeshc134, offers AI-powered photo compositing tools for Photoshop. The project has garnered significant interest with 152 stars and a growth score of 18.80, indicating its relevance to professional designers looking for advanced compositing solutions.

Ai-Pixel-Design-Archive, maintained by abnormal-codex, is described as the best AI image generator for professional designs in 2026. With a growth score of 18.77 and 151 stars, this project seems to attract users interested in high-quality design tools powered by artificial intelligence.

SenseNova-Vision, developed by OpenSenseNova, is gaining traction with its unified multimodal generation approach. This repository has amassed 371 stars and a growth score of 12.13, indicating strong community interest in innovative approaches to integrating vision across different modalities.

Nova-image-studio from tianjiangqiji offers an AI-driven image generation platform that supports custom models, multimodal operations, and real-time task management. The project's 221 stars and growth score of 11.31 suggest growing interest in its versatile capabilities for both professional and casual users.

4k-image-api, by jianjianai, provides an OpenAI-compatible API service for generating high-resolution images using various providers. With a growth score of 6.56 and 81 stars, this project is attracting developers looking for flexible image generation solutions that integrate seamlessly with existing workflows.

While some projects are more niche in focus, LongE2V by cdfan0627 stands out as an innovative approach to long-horizon event-based video reconstruction. With a growth score of 3.78 and 32 stars, this project is gaining attention from researchers interested in advanced video prediction techniques.

Lastly, foto-kita-blur, created by claramiadevira, offers a simple Python project that blurs the webcam when it detects a peace sign. Despite its simplicity, the project has attracted 57 stars and a growth score of 3.27, suggesting interest in creative applications of computer vision technology.

These projects collectively showcase the dynamic landscape of AI-driven image and video generation tools, catering to diverse needs from personalization and enhancement to advanced compositing and prediction techniques.
Back to all reports