baidu/Unlimited-OCR
Image-Text-to-Text β’ 3B β’ Updated β’ 2.6M β’ 3.61k
Get a music sample inspired by the mood of an image
Generate text using the Phi language model
Generate depth map from a single image
Dub videos in another language with cloned voice
Generate 3D human motion from text prompts
Generate music from a text description and optional melody