Image composition with pre-trained diffusion models

A technique to increase control over the images generated by pre-trained text-to-image diffusion models

Text-to-image diffusion models have achieved stunning performance in generating photorealistic images adhering to natural language description prompts. The release of open-source pre-trained models, such as Stable Diffusion, has contributed to the democratization of these techniques. Pre-trained diffusion models allow anyone to create amazing images without the need for a …

ai art author control diffusion diffusion models generated image image diffusion images language natural natural language performance photorealistic pre-trained models prompts release stable diffusion text text-to-image text-to-image-generation