Generate animated videos from configuration files

Generate 3D room layouts from RGB panoramas

Answer questions about images by chatting

Demo for DocLayout-YOLO

Track, rank and evaluate open Arabic LLMs and chatbots

image captioning, VQA

Ultra-high resolution image synthesis

Generate detailed step-by-step answers to questions

Display OCRBench leaderboard for model evaluations

Ask any questions to the IPCC and IPBES reports

Interpret and execute code with responses

Extract text from images using OCR

Media understanding

Remove image backgrounds with a click

Generate summaries for long-form text

Generate speech from text with reference audio

An end-to-end (e2e) Voice Language Model by Fish Audio.

View how beam search decoding works, in detail!

In-browser image background removal

FLUXllama Multilingual(to be add more languages)