Three passes down the denoise ladder

One big jump, or three small ones

The usual way people use img2img is a single pass: load the reference, pick a denoise value, generate, look, adjust the number, repeat. It works, and it is worse than the alternative for a reason that is easy to see once stated.

At a single middling value, 0.55, say, the model has to do two jobs at once: reorganise the image substantially, and finish it convincingly. It is being asked to make a large change and a refined one in the same pass, and one of them suffers. Either the composition survives and the surface stays rough, or the surface is beautiful and the composition has drifted.

The ladder splits the jobs.

pass 1   denoise 0.75   establish the look, accept large change
pass 2   denoise 0.50   fix what pass 1 got wrong, hold composition
pass 3   denoise 0.30   finish surface and light, change nothing structural

Each pass takes its predecessor as input. Same prompt, same seed or not, only the strength moves.

What the numbers actually do

Denoise strength decides how far back toward pure noise the image is pushed before denoising begins. At 1.0 nothing of the input survives; at 0.0 nothing changes. Between those, the number is roughly the proportion of the sampling schedule that runs.

Useful landmarks, which hold across most models:

• 0.15 to 0.25: texture and grain only. The picture is identical.
• 0.30 to 0.40: surfaces, light quality, small detail. Composition untouched.
• 0.45 to 0.60: the working range. Real change, recognisable source. Objects can move slightly, expressions change, materials change completely.
• 0.65 to 0.75: the source is now a suggestion. Composition survives loosely, content may not.
• 0.80+: the input is contributing little beyond a colour distribution.

The ladder works because 0.30 applied to a nearly-right image is a completely different operation from 0.30 applied to a rough one. Each rung starts from something better than the last did.

Where this is the right tool

Bringing a rough render up. A sketch, a 3D blockout, a crude collage. Start at 0.7 to make it photographic, then descend.

Changing a material. Concrete to timber, plastic to ceramic. Two passes at 0.5 and 0.3 with the material named in the prompt.

Matching a look across a set. Take frame nine, run it at 0.3 with the anchor’s prompt, and its light and grade move toward the rest of the set without its content moving.

Rescuing a frame that is nearly there. One pass at 0.35 often repairs the general softness that makes an image feel unfinished.

The way it goes wrong

Colour drift. Each pass nudges the palette, usually warmer and more saturated, because each pass re-imposes the model’s own bias. Three passes compound it. Check the grade after the ladder and correct it once at the end rather than fighting it on every rung.

Contrast crush. The same compounding applies to contrast; blacks get blacker each time. If your third pass looks heavy, this is why.

Loss of the thing you liked. The reason you chose that frame was some specific quality, and three passes of averaging tends to sand it off. Keep the original open in another window and compare, not just the previous rung.

Detail invention. At 0.5 and above the model will add things that were not there: a pattern on a wall, a reflection, an extra object. On a product shot this is a correctness problem, not a style one.

The limitation to understand

Img2img cannot move something across the frame. It has no notion of objects; it is denoising a whole latent toward a distribution consistent with the prompt. A chair on the left stays on the left, or becomes something else on the left.

So the ladder is the wrong tool for “move the subject right and give me more sky”. That is outpainting, or a control image, or a new generation. When somebody spends forty minutes raising denoise to try to reposition a subject, this is what they have missed: by the time the strength is high enough to move it, the strength is also high enough that nothing else survives either.

The right division is that img2img changes what things are made of and how they are lit. Controls, which the rest of this block covers, change where things are. Reaching for the wrong one is the single commonest waste of time in this part of the work.