PetGPT is a lightweight, open-source desktop pet app that combines nostalgic virtual pet interaction with modern AI chat—offering proactive, context-aware conversations and deep customization.
Seamless Communication is Meta AI's research-grade real-time multilingual speech translation system enabling low-latency voice-to-voice and voice-to-text conversion across nearly 100 languages.
Animate Anyone is an open-source AI framework that converts still images of people or characters into high-fidelity, pose-controllable animated videos—ideal for dance generation, fashion demos, and expressive digital storytelling.
StoryMaker is an open-source AI image generator that creates consistent, narrative-ready character images across multiple prompts using facial encoding, LoRA, and cross-attention control.
Outfit Anyone is an open-source AI system that realistically overlays clothing onto people in images—enabling virtual try-on without physical garments or 3D scans.
PhotoMaker V2 is a free, web-accessible AI image generator that creates highly realistic, consistent, and customizable human portraits from text prompts using advanced diffusion and face-aware adaptation techniques.
MagicVideo-V2 is an open research AI framework by ByteDance for generating high-resolution, fluent, and aesthetically enhanced videos from text prompts using a modular end-to-end pipeline.
AnyText is a diffusion-based open-source tool that generates and edits multilingual text directly into images with high fidelity, supporting curved layouts, multi-line placement, and seamless background fusion.
Screenshot to Code is an AI-powered tool that converts website screenshots into clean, editable HTML, CSS, and JavaScript code — accelerating frontend development with intelligent visual-to-code translation.
Real-ESRGAN is an open-source AI model that dramatically enhances low-resolution images using blind super-resolution and synthetic degradation modeling—no high-res reference needed.
Ovis1.6 is an open-source multimodal large language model designed for joint text and image understanding, excelling in math reasoning, object recognition, and cross-modal analysis.
DemoFusion is an open-source AI framework that generates ultra-high-resolution images (up to 4096×4096+) from low-res inputs using progressive upscaling—no extra training or expensive hardware required.
RapidPages is an open-source AI coding assistant that turns natural language descriptions into production-ready React and Tailwind CSS UI components in real time.
Draw an Audio is a research-grade AI system that automatically generates contextually accurate, temporally aligned sound effects from silent videos using multimodal conditioning.
ActAnywhere is a research video generation model that automatically creates temporally consistent, motion-aware backgrounds for foreground subjects—enabling seamless background replacement and visual effects without manual keyframing or green screens.
Void is an open-source, AI-enhanced code editor built on VS Code that delivers intelligent autocompletion, inline editing, context-aware search, and full prompt visibility for developers.
Vary-toy is a compact, open-source visual language model enabling document OCR, image description, visual question answering, and multimodal dialogue on consumer-grade hardware.
Follow Your Pose is an open research framework that generates highly controllable, temporally coherent videos from text prompts and user-specified human pose sequences.
IP-Adapter is an open-source adapter that lets you guide Stable Diffusion and similar models using image prompts—enabling accurate, controllable image generation without fine-tuning.