Creación y multimedia · GitHub

制作统一漫画墨线风格的解释图与透明角色插图，用于概念、流程、比较和文章配图。

[ICML 2026] GenExam: A Multidisciplinary Text-to-Image Exam

Drop-in replacement for Graphics but with anti-aliasing

AI Image Generation Discord Bot @ pollinations.ai 🌸 Used in 1.5k+ servers

• Users can also speicify whether they want to AI enhance their prompt or not.
• Users can also specify the width and height of the image.

BLE Sync Cycle is a Go application designed to synchronize video playback with real-time cycling data from Bluetooth Low Energy (BLE) devices, such as cycling speed and cadence (CSC) sensors

• Real-time synchronization between cycling speed and video playback
• Support for compliant BLE Cycling Speed and Cadence (CSC) sensors (in speed mode)

📱 A native iOS & Android client for ComfyUI — run AI image generation workflows from your phone

• Native Experience - Built with React Native and Expo for a smooth, responsive native feel.
• Real-time Monitor - Watch generation progress step-by-step and preview results instantly. Jobs keep running when you leave the screen or background the app, and are picked back up when you return.

跨平台视频播放器，支持导入自己的影视源和 IPTV 直播源。

Merge multiple MediaStreams into one composite (realtime - in the browser!)

PixaPencil is a sleek and user-friendly pixel art editor for Android, designed for both novice and expert artists.

Download Adobe Illustrator for Windows 10 and 11 using this direct installer.

• Vector Scaling: Create graphics that you can resize without losing clarity.
• Typography Tools: Access a library of fonts for text design.

Official code for InfoVis: one 9B model for slide image generation and editing, with the VisSlideBench benchmark and 15M+ training records.

• One model, four slide tasks: input images serve as a style reference, content assets, or the slide to edit.
• Slide-native data and benchmark: over 13M continual-pretraining and 1.9M SFT records, and VisSlideBench, 1,527 manually screened cases with task-specific metrics.

Wan 2.7 Image API (`wan2.7-image`): model id, pricing, parameters and copy-paste examples for the OpenAI-compatible APIMart endpoint.

Wan 2.7 Image prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-image`) and the cost per image.

[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding

Wan 2.7 Image prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`wan2.7-image`) and the cost per image.

Z Image Turbo prompts: tested image prompt recipes with example renders, aspect ratios, the model id (`z-image-turbo`) and the cost per image.