Apply style to an image

Generate lip-synced video using audio

Generate detailed captions from images

Tag images with auto-generated labels

Turn text into speech with customizable voice, rate, and pitch

Measure over-refusal in LLMs using OR-Bench

Demo for MiniCPM-o 2.6 to answer questions about images

Document Retrieval

Generate task-specific instructions and responses from text

Extract PDFs and chat to get insights

Convert audio using voice models and separate vocals

Turn black and white images into color

User FriendlyImage & Video Upscaler!

Launch a web interface for text generation

Detect AI-generated images by analyzing texture contrast

Generate realistic talking heads from image+audio

Extract melody from an audio file

Detect objects in images using YOLO

Replace and enhance parts of images based on prompts

Reconstruct and convert voice audio