Text-to-Image world model with Cosmos2
GANs are so back!
Generate images from text prompts
Optical illusions and style transfer with FLUX
Display images from URLs
Run iterations and produce output
Create outpainting video from an image
Demo fo Dream 7B, an open diffusion large language model
New FaceID model trained on an open dataset
Large Language Diffusion Models
Explore fun LoRAs and generate with SDXL
Generate images using text and reference images
Structure and Appearance Control
Generate captions and analyze images with various tasks
Create lifelike animated videos using a photo and audio
Find music that matches your description
Replace any hair with a reference image