Upside down reinforcement learning for text-to-image generation

A method comprising:

• obtaining a training set comprising a training image and a training prompt that includes an image quality level;
• generating, using an image generation model, a synthetic image based on the training prompt;
• and
• training, using the training set and the synthetic image, a diffusion prior model to generate an image embedding that represents the image quality level.

An apparatus comprising:

• at least one processor;
• at least one memory storing instructions executable by the at least one processor;
• a diffusion prior model comprising parameters stored in the at least one memory and trained to generate an image embedding based on an input prompt including an image quality level and a description of an object, wherein the image embedding represents the object and the image quality level in a vector space;
• and
• an image generation model comprising parameters stored in the at least one memory and configured to generate a synthetic image based on the image embedding, wherein the synthetic image depicts the object and has the image quality level.