🎥 Create stunning videos with LTX-Video, a powerful model for advanced motion editing and video manipulation in your projects.

🚀 Optimize mixed advantage policies in reinforcement learning to enhance foundation model performance on reasoning tasks.

📝 Create and run your AI Studio app effortlessly with Nano-Banana-Editor. Easily manage your dependencies and deploy locally for smooth development.

🚀 Simplify FLUX access with 4-bit models and CPU offloading, enabling powerful GPU utilization and prompt generation from keywords with DeepSeek-R1 AI.

🍌 Generate stunning images and edit them conversationally with the powerful NanoBananaEditor, built on React and TypeScript using AI technology.

(Accepted by IJCV) Liquid: Language Models are Scalable and Unified Multi-modal Generators

Smart and Simple Flux for GPU-poor

Animatic Vision Client is the Next.js frontend for the Animatic Vision platform — an AI-powered system that transforms written stories into dynamic visual animations.

[CVPR 2025 Oral]Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

🤗 Generate images with diffusion models.

ICCV 2025 | ROVI: A 1M-scale dataset with comprehensive image descriptions and open-vocabulary bounding box annotations for instance-grounded text-to-image generation

Smoke Classification Using Transfer Learning ang GenAI with Distributed Multi-GPU Parallel Training.

UniWorld: High-Resolution Semantic Encoders for Unified Visual Understanding and Generation

LTX-Video Support for ComfyUI

AnimeGen is an AI-powered tool that takes a written story as input, automatically splits it into meaningful scenes, and generates anime-style images for each scene. It then displays these images in a slideshow, creating a visual storytelling experience.

Visualize-It — A MERN stack web app that generates high-quality images from text prompts using the Clipdrop API. Users can type any description and instantly visualize it as an AI-generated image. ✨

GenExam: A Multidisciplinary Text-to-Image Exam

Violet Tools 💅 is the beauty brain of your ComfyUI workflow. Each node speaks a different aesthetic language: quality, scene, body, glamour, pose, vibe... until the Encoding Enchantress weaves them into a polished, weight‑aware conditioning tapestry. Save and load consistent characters, audit token flow, experiment with blend modes, and have fun!

[AAAI 2025]👔IMAGDressing👔: Interactive Modular Apparel Generation for Virtual Dressing. It enables customizable human image generation with flexible garment, pose, and scene control, ensuring high fidelity and garment consistency for virtual dressing.