A Unified Framework for Image Customization
Run tasks using an AI-powered computer agent
Convert 3D models into primitive assemblies
One framework to Generate multi-view images without Lora
Create 3D models from videos or images
A Step Towards Music Generation Foundation Model
A single-feed-forward method that predicts unseen 3D
plug-and-play with visual concepts
Universal Image Editing is worth a single LoRA
Generate realistic talking video from an image and audio
Request evaluation for new speech models
Transcribe audio to text with timestamps
Edit an image based on the given instruction.