Vui
NotebookLM conversational speech model
Generate images from text prompts
Ultra fast high quality image generation
FLUXllama Multilingual(to be add more languages)
Structure-Preserving Style Transfer with Canny, Depth & Flux
Transform images into artistic styles
Wan: Open and Advanced Large-Scale Video Generative Models
Generate personalized character images with text prompts
Generate customized images using text and multiple images
Chat with images, videos, or PDFs to generate text
Generate any application with DeepSeek
Generate 3D video from input images
Large Animatable Human Model
Generate text and speech from text, audio, images, and videos
New Ghibli EasyControl model is now released!!