Generate music using descriptions and optional melody audio

Evaluate open LLMs in the languages of LATAM and Spain.

Video Gallery of Dokdo

Convert Stable Diffusion checkpoint to Diffusers and open a PR

Generate annotated video with object detection

Generate images based on text prompts

State-of-the-art Object Detection YOLOV9 Demo

Apply the motion of a video on a portrait

Generate audio and SRT subtitles from text

Extract text and metadata from PDF files

text2text models for document summarization

Download and prepare voice conversion models

User Friendly Image & Video Upscaler!

Render beautiful graphics with Moondream WebGPU

Prompt with Images in flux[dev]

CPU powered, low RTF, emotional, multilingual TTS

StyleTTS2 trained on ukrainian dataset

Create a mask for uploaded image

Music Generation - text to music, music continuation.