VLMEvalKit Eval Results in video understanding benchmark

Communicate with a multimodal chatbot

Flux Animations(GIF) Generaion

Generate military-themed images using prompts

Cut out objects from images using prompts or bounding boxes

Generate clean audio from noisy recordings

Generate text based on an image and prompt

Make Custom Voices With KokoroTTS

Chatbot

Convert images to LaTeX code

Video captioning/tracking

Generate high-fidelity audio from input audio waveforms

Generate a Logo in 2 clicks

Generate a video from text prompts

Turn Any Article to Podcast

Swap faces in videos

Video upscaler/restorer

Compare AI models by voting on responses

Video Super-Resolution with Text-to-Video Model

Display animated 3D scenes using web technology