baidu/Unlimited-OCR
Image-Text-to-Text β’ 3B β’ Updated β’ 213k β’ 1.14k
Ask questions and get detailed answers
Generate virtual tryβon images of a person wearing a chosen garment
Style-Preserving Text-to-Image Generation
Generate personalized images preserving your face identity
Replace objects in images using prompts or reference images
Generate speech in a cloned voice from a short audio clip
Generate music from a text description and optional melody
Transcribe audio or YouTube videos to text
Transcribe audio files to text instantly