Conditioned & Edited Image Generation
One frozen denoiser, steered by adapters — for character consistency, and for forgery
Architecture introduced 10 Feb 2023
This is the engine behind 'make a picture of THIS exact character, in THIS pose, and change only THIS part'. A single big image model stays frozen; small add-ons bolt onto it to do the steering. Style add-ons (LoRA) reskin it, a 'guide-rail' add-on copies a pose or a reference picture's look, a face fingerprint pins one person's identity, and a masking tool confines edits to one spot so the rest of the photo is untouched. The catch: the reference pictures and the add-ons come from the open web — anyone can author them — so the same machinery that keeps a character consistent also makes seamless deepfakes and doctored photos.
Follow a request · step 1 of 6
You write a prompt, optionally paint a mask over the area to change, and drop in a reference picture — say, a photo of a character (or a person) you want to appear.