Hacker News Reader

Try converting the images to grayscale, then setting the denoising strength very low and prompting for the exact colors you want things to be.

When you afford SD img2img influence with a high strength parameter, so it can change the colors of a photo, you also are letting it have enough influence to redesign the room at random and not just changing the colors

Dreambooth trained on the ground truth photos might help a bit

I’d love for there to be a form of frequency separation, where we could keep the details but mess with the colors/less major details.

Photographers have been attempting to emulate various films in different ways forever. Stable diffusion could do it absolutely perfectly.

This seems much easier in an app like photoshop/affinity if you want to keep everything really static. Or by using a combination of photoshop and then SD to clean up.