Comfy-Org/Ideogram-4
Updated • 144k • 277
8B CSM-style text-to-speech with voice cloning
Create 3D Gaussian model from a 2D image
Generate speech audio from text
Ideogram 4 state of the art open weights
NVIDIA Cosmos3-Nano — text/image to video + audio
Chat with an AI using text, images, audio, or video