Segment objects in videos with point clicks

Create personalized avatars from images

Generate lifelike video animations from images and audio

The Metropolitan Museum of Art Collection

Generate images from text prompts with customizable styles

Track, rank and evaluate open LLMs and chatbots

Generate animated videos from images and prompts

Demo for https://github.com/Byaidu/PDFMathTranslate

Generate audio with voice conversion

Transcribe audio with emotions and events

Find images matching a text query

"One-minute creation by AI Coding Autonomous Agent MOUSE"

Generate text using Transformer models

Consistency generation of portrait and subject

Generate music from text and melody

Generate an animated GIF from a text prompt

diffusion-based Image Restoration model

Open LLM(CohereForAI/c4ai-command-r7b-12-2024) and RAG

VGGT (CVPR 2025)

Create and validate structured metadata for datasets