What is the correct order for these stages?

Generate first, then face-restore the small native face, then upscale the whole image, then inpaint any fixes at the higher resolution, then export. Restoring before upscaling and inpainting last keeps each tool working at the resolution it does best.

Why upscale before inpainting and not after?

Inpainting at the final resolution lets you fix details at full size and blend them cleanly. Inpainting first and then upscaling can soften or distort the very region you just repaired.

Are the time estimates per image or per batch?

They are per single image at the chosen settings. Multiply by your batch size for a full run, and remember stages like export are near-instant while upscaling and generation dominate the total.

Can I run this whole chain in one tool?

Yes — ComfyUI lets you wire all of these stages into a single graph that runs end to end, and Automatic1111 supports most via the img2img tab plus extensions. This planner gives you the stage order and time budget before you build the graph.

Prompt Chaining Workflow Planner

Prompt chaining workflows

Great AI images rarely come from a single generation. A real pipeline chains stages: generate a base image, restore the face, upscale, inpaint problem areas, then export. Get the order wrong — upscale before face restore, inpaint before upscale — and you fight your own tools. This planner assembles the correct order and estimates the total processing time per image.

How it works

Each stage has a rough per-image cost that scales with your GPU tier. The planner holds the proven execution order and sums only the stages you enable:

generate → face-restore → upscale → inpaint → export
total_time = Σ stage_time(enabled stages, gpu)

Generation and upscaling dominate the budget; export is effectively free. Running face restore on the small native face (before upscaling) and inpainting at the final resolution (after upscaling) is what keeps quality high.

Tips for building the chain

Restore early, inpaint late. Fix faces at native size, fix everything else after upscaling.
Upscale once. A single good 2×–4× pass beats stacking several small ones, which compounds softness.
Mask tight for inpaint. Smaller masks at high resolution blend more cleanly and run faster.
Build it in ComfyUI. A saved graph runs the whole chain unattended across a batch — ideal once the planner confirms your time budget.