baidu/Unlimited-OCR
Image-Text-to-Text • 3B • Updated • 1.42M • 4.33k
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 into another language with cloned voice
Generate 3D human motion from text prompts
Generate music from a text description and optional melody
Edit videos with text prompts via diffusion
Chat with an AI assistant using text and images
Convert and separate audio using models and TTS
Complete list of past Daily Papers
FaceOnLive On-Premise Solution