Apply the motion of a video on a portrait

Qwen2.5-VL 7B & 3B

Explore multilingual LLM benchmark results

Generate summaries from YouTube videos or uploaded videos

Interact with Florence-2 to analyze images and generate descriptions

Generate React TypeScript App

Video captioning/tracking

Enhance images with high-resolution quality and HDR effects

Chatbot

Upscale images to x4

Generate sound effects for silent videos

Display visual document retrieval leaderboard

Track, rank and evaluate open LLMs and chatbots

Convert text to speech using Microsoft Edge TTS

Document Retrieval

Generate insights from charts using text prompts

Analyze images to generate captions, detect objects, or perform OCR

Generate detailed lineart images from simple prompts

Generate realistic talking heads from image+audio

Generate depth maps from images