Caption images with detailed descriptions using Danbooru tags

Repair images by removing unwanted parts

Create a talking video from text, voice, and image

Generate 3D models from images

Find financial answers from images

Clarity AI Upscaler Reproduction

Generate a video from an input image and prompt

Detect objects in images

Detect objects in images

Generate a modified audio track and beat image from an uploaded song

Transfer GitHub repositories to Hugging Face Spaces

Tag images to find ratings, characters, and tags

Replace background in images with new scenes

Generate videos and key frames from a single image

Analyze sentiment of a text input

Generate voice from text

Generate multilingual speech using text input

Test your attribute inference skills with comments

Apply the motion of a video on a portrait

Gradio demo of CharacterGen (SIGGRAPH 2024)