Diffusion Transformer - Edgentiq

oboro: A New Text-to-Image Model for High-Quality Generation on Limited, Copyright-Cleared Data

MUG-V 10B: Advancing High-Efficiency Training for Large Video Generation

DiTSinger: Advancing Singing Voice Synthesis with Scalable Data and Implicit Alignment

DiT-VTON: Advancing Virtual Try-On for Diverse Products and Enhanced Editing

Tenma: A New Approach to Versatile Robot Manipulation

spot_img

Recently Added

Predicting 3D Geometry Using Advanced Image Editing AI

Read more

Tencent’s Hunyuan Video-Foley AI Achieves Breakthrough in Lifelike, Synchronized Audio for AI-Generated Video

Read more

ROSE: A Unified Framework for Removing Objects and Their Environmental Effects in Videos

Read more

Gen AI News and Updates

spot_img

- Advertisement -

oboro: A New Text-to-Image Model for High-Quality Generation on Limited, Copyright-Cleared Data

November 12, 2025

MUG-V 10B: Advancing High-Efficiency Training for Large Video Generation

October 21, 2025

DiTSinger: Advancing Singing Voice Synthesis with Scalable Data and Implicit Alignment

October 13, 2025