Convert PDF to text using OCR

Prompt with Images in flux[dev]

Generate depth map from images

Generate depth video from input video

Extract text from images using OCR

Separate vocals from instrumental music in audio files

interactive demo for cube 3d model

Track, rank and evaluate open Arabic LLMs and chatbots

Generate subtitles for YouTube videos

Generate 3D room layouts from RGB panoramas

image captioning, VQA

Generate voice from text using reference audio

Generate a video from a prompt and an image

Media understanding

Answer questions about images by chatting

Qwen2.5-VL 7B & 3B

Explore BERT model interactions

Generate images from text prompts

Replace characters in a video with characters in photos

Generate summaries for long-form text