vikhyatk/moondream2
Image-Text-to-Text โข 2B โข Updated โข 2.45M โข 1.42k
Generate detailed Stable Diffusion prompts from any image
Generate voice-over with text prompt
Generate speech from text using a reference voice
Generate images from text or photos in realโtime
Generate and clone voices from text or audio
Generate animated videos from images and motion sequences
Generate videos from text prompts
Convert voice to another voice
Clone a voice and generate speech