
nari-labs/Dia-1.6B-0626
Text-to-Speech
•
2B
•
Updated
•
78.1k
•
88
Control 3D models using hand gestures and voice commands
Generate protein fitness scores and visualizations
Ultra Fast FLUX Kontext Dev for Image Editing
Audio-Driven Multi-Person Conversational Video Generation
edit images with Kontext and LoRAs
Hand-controlled arpeggiator, drum machine, and visualizer
Generate text responses to images, videos, and audio
Kontext multi image composition on FLUX[dev]
LightGlue demo
Convert web content to JSON using a custom schema
OmniGen2: Unified Image Understanding and Generation.
Generate or edit images using text prompts