Sketch animation with AI-powered simplicity and creativity.
Effortless Animation: FlipSketch transforms static sketches into smooth animations with just a drawing and a text description.
AI Innovation: Combines text-to-video...
How RedPajama datasets are redefining AI development with transparency, scalability, and versatility.
Transparency in AI Training: RedPajama introduces an unprecedented level of openness in dataset composition,...
The groundbreaking framework for consistent, customizable video generation opens new doors for filmmakers and VR designers.
Versatile Control: AnimateAnything enables precise video manipulation through camera trajectories,...
Achieving scalable and flexible part-level segmentation without text prompts, SAMPart3D enables advanced 3D editing and model customization.
Text-Free, Scalable Segmentation: SAMPart3D removes the need for...
OMNI-EDIT leverages specialist guidance to tackle seven unique editing tasks, achieving unprecedented accuracy and quality in real-world image editing.
Multi-Task Capability: OMNI-EDIT is designed to...
StdGEN offers an advanced pipeline for high-quality, semantically decomposed 3D characters ready for gaming, VR, and film production.
Fast, High-Quality 3D Generation: StdGEN creates intricately...
A Million-Scale Dataset Brings New Potential to Image-to-Video Generation Models
Unprecedented Scale and Scope: TIP-I2V introduces over 1.7 million unique text and image prompts for...
From subtle smirks to bold expressions, X-Portrait 2 transforms static images into lifelike animations for film, virtual agents, and more
Advanced Expression Encoding: X-Portrait 2...
This groundbreaking dataset and framework achieve robust garment modeling from in-the-wild images, addressing challenges of complex poses and deformations.
Advanced Dataset: GarVerseLOD introduces a large-scale...
With its new modular architecture, Magentic-One tackles complex tasks across domains, promising a future of AI-driven workflows.
Multi-Agent Capabilities: Magentic-One uses a modular, multi-agent design,...
New AI Method Embeds High-Fidelity Visuals and Exaggerated Expressions, Opening Doors for Creative and Open-Source Applications
Spatial Knitting Attentions: HelloMeme introduces spatial knitting attention mechanisms...
A New Approach to Extract and Identify Multiple Intents in Complex User Queries
Qualcomm’s research introduces a Pointer Network-based system designed to handle multiple intents within a...
