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.
Draw an Audio is a research-grade AI system that automatically generates contextually accurate, temporally aligned sound effects from silent videos using multimodal conditioning.
Follow Your Pose is an open research framework that generates highly controllable, temporally coherent videos from text prompts and user-specified human pose sequences.
V-JEPA is an open-source, self-supervised video foundation model that learns visual representations by predicting masked frame features—enabling robust video understanding without labels.
Boximator is an open-source video synthesis tool that enables precise object motion control in videos using hardhttps://www.aitopic.com/soft bounding box constraints and self-tracking techniques.
DiT is an open-source image generation model that replaces convolutional U-Nets with Transformers in diffusion models to produce high-fidelity, scalable, and controllable synthetic images.
OmniGen is an open-source unified diffusion model that handles text-to-image generation, image editing, subject-driven synthesis, visual conditioning, and even classic CV tasks—all within a single streamlined architecture.
VideoDoodles is a free, web-based research prototype from Adobe Research that lets creators draw and animate hand-drawn elements directly onto videos using AI-powered scene-aware canvases.
EchoMimic is an open-source tool that creates lifelike digital human animations driven by audio and facial landmarks for expressive, multilingual talking avatars.
JoyHallo is an open-source digital human model that generates high-fidelity, audio-driven talking-head videos in Mandarin and English using optimized semi-decoupled architecture.
Motionshop is an open-source framework that replaces real people in videos with expressive, lighting-aware 3D digital humans while preserving natural motion, timing, and visual continuity.
Alibaba Cloud's Tianchi hosts large-scale AI competitions with open datasets and free compute, letting developers test algorithms on real-world problems.
实在Agent is an enterprise AI office assistant that understands spoken instructions and directly operates software on computers, phones, and car screens to complete work tasks.