Adobe inc. (20250117967). UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS
UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS
Organization Name
Inventor(s)
Ritiz Tambi of San Francisco CA US
Ajinkya Gorakhnath Kale of San Jose CA US
Pranav Vineet Aggarwal of Santa Clara CA US
Nikolaos Vlassis of San Jose CA US
UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS
This abstract first appeared for US patent application 20250117967 titled 'UPSIDE-DOWN REINFORCEMENT LEARNING FOR IMAGE GENERATION MODELS
Original Abstract Submitted
a method, apparatus, non-transitory computer readable media, and system for image generation include obtaining an input text prompt and an indication of a level of a target characteristic, where the target characteristic comprises a characteristic used to train an image generation model. some embodiments generate an augmented text prompt comprising the input text and an objective text corresponding to the level of the target characteristic. some embodiments generate, using the image generation model, an image based on the augmented text prompt, where the image depicts content of the input text prompt and has the level of the target characteristic.