Re:OpenAI releases image generation in the API
by AuryGlenz on Friday April 25, 2025 @02:04AM
(#43790599)
95% of what I do with image models is train LoRAs/finetune family and friends and create images of them.
Sure, I can ghiblify specific images of them on this model, but anything approaching realistic changes their looks. I've also done specific LoRAs for things that may or may not be in their training data, such as specific movies.
Sure, I can ghiblify specific images of them on this model, but anything approaching realistic changes their looks. I've also done specific LoRAs for things that may or may not be in their training data, such as specific movies.