Generate 3D character models from single images

Generate image captions with different models

Line Art Colorization with Precise Reference Following

Flux.1 Fill

Create 3D reconstructions from videos or images

Generate audio from text in multiple languages

Upload documents and chat with a smart assistant based on them

Generate customized audio from text using a voice sample

Browse and submit evaluation results for AI benchmarks

Extract text from images

View and submit LLM benchmark evaluations

Huggingface demo of TrajectoryCrafter

Generate flow or disparity from two images

FLUX.1-Schnell on serverless inference, no GPU required

Swap Single Face

Remove background from live video feed

Identify objects in images using text queries

Create a presentation PPTX from text prompts

Follow visual instructions in Chinese

Generate music tracks with instrument settings