nari-labs/Dia-1.6B
Text-to-Speech β’ 2B β’ Updated β’ 5.55k β’ β’ 2.88k
Generate customized images from text and reference photos
Relight photos with AI using custom lighting prompts
Generate virtual tryβon images of a person wearing a chosen garment
Generate detailed Stable Diffusion prompts from any image
Generate music from a text description and optional melody
GPT 4o like bot.
Generate images from text prompts
Set up and customize Stable Diffusion WebUI