4M Demo
4M: Massively Multimodal Masked Modeling
4M: Massively Multimodal Masked Modeling
Generate images from text prompts
Generate stunning high quality illusion artwork
A demo of OpenDalle V1.1 on a ZERO GPU.
Super-fast image generation on SDX
Create a 1M faces 3D colored model from an image!
Text-to-Image
High quality image generation in 3 second
Generate customized real photos from images and prompts
Future-oriented Anime model
Apply the motion of a video on a portrait
Generate images from text prompts with customizable LoRA
Interact with Florence-2 to analyze images and generate descriptions
Generate summaries from YouTube videos or uploaded videos
Generate photorealistic images from text
Generate images from text prompts
The most opinionated, anime-themed SDXL model
Generate customized face images with styles