Upscale images using AI-powered models

Translate text between multiple languages

西北工业大学ASLP实验室OSUM项目demo展示

Scalable and Versatile 3D Generation from images

Convert audio to different voice

faceswao

Convert a GitHub repo to a text file for any LLM to use

Generate 3D models of various objects

Enhance and upscale images for better quality

training free image editing with Flux

Separate audio into vocals, bass, drums, and other

Predict credit card approval using encrypted data

Colorize grayscale images

Multimodal Language Model

Efficient Track Anything

Compare different visual question answering

Implement Gemini2 Flash Thinking model with Gradio

Generate protein structures from specified lengths and seeds

Music Genre Classifier

MaskGCT TTS Demo