ai-image-editing

これはレビュー時に保存された抜粋です。完全で最新の内容は外部ソースを確認してください。

---
name: ai-image-editing
description: >-
  The AI image-editing router — inpainting/object removal, background removal, upscaling,
  outpainting, old-photo restoration, and retouch, routed task-first to the right engine. Use when
  someone wants to remove an object/person from a photo, cut out backgrounds, upscale an image,
  extend an image to new aspect ratios, restore an old photo, fix a generated image, or asks which
  editing tool to use. Uses the TOUCH framework. Reads brand-profile + design-and-templates first.
  The agent names the task, routes to the right engine, writes the spec, and can call APIs where
  connected; the HUMAN judges every result at 100%; WoopSocial publishes. Honesty spine: an edited
  real photo is an edited claim — creative upscalers hallucinate detail (never on
  products/documents), no defect concealment, body-retouch disclosure honored, no
  watermark/provenance stripping. Distinct from image-prompt/flux/nano-banana (generation), canva
  (the design workflow), and before-after-and-transformation (the claim rules).
version: 1.0.0
---

# ai-image-editing

The **edit router** — name the task, route the engine, one change at a time, uphold the real, check the seams,
hand off with rights. The agent routes + specs; the **human judges every result at 100%**; **WoopSocial
publishes**. (Ships with `tools/integrations/ai-image-editing.md`.)

## The POV: fix the 5%, keep the 95% — and remember an edited photo is an edited claim
Editing's promise is surgical: the 2026 engines removed the old excuses (background removal now handles hair and
glass; inpainting understands scene light; expand extends convincingly). The top-1% operator holds three lines
the tool marketing won't. **(1) The upscaler split is an honesty split:** *faithful* upscalers (Topaz-class)
preserve what's there; *creative* upscalers (Magnific-class) **hallucinate convincing detail that wasn't in the
original** — spectacular for art, a fake-product-photo generator for commerce (invented stitching on a bag = a
false claim, not sharpening). In-image text gets mangled — re-typeset it; no upscaler beats a reshoot.
**(2) Editing real photos crosses into misrepresentation faster than generating:** defect concealment fails the
FTC net-impression standard, undisclosed body retouching is **label-required by law in several markets**
(France, Norway including influencers, Israel), and chained face enhancement can drift a real person's identity
— the person who knew them judges likeness. **(3) Route by task, not brand loyalty:** raw complex-mask quality
lives in FLUX Kontext/Fill; **indemnified client work lives in Firefly** (the only major engine trained
exclusively on licensed content); quick fixes stay in Canva; product batches go to dedicated pipelines.

## Read these first
1. **brand-profile** + **design-and-templates** — the system the edited image must still fit.
2. **before-after-and-transformation** — the claim rules for any results/comparison imagery.

## The framework: TOUCH
(Depth: `references/the-touch-framework.md`.)
- **T — Task first, tool second:** name the job (remove/replace/erase-bg/extend/upscale/restore/restyle), then
  route it — the task defines the tool, never the reverse.
- **O — One change at a time:** small precise masks; chained small edits; re-check coherence every few steps;
  upscale low-res sources BEFORE inpainting; preserve the 95%.
- **U — Uphold the real:** faithful mode for products/documents; no defect concealment; retouch-disclosure laws;
  conservative face work; consent; no watermark/provenance stripping; hallucination belongs to art.
- **C — Check the seams:** 100% zoom, always — edges/halos, light + shadow direction, perspective, faces,
  in-image text, batch consistency, identity drift.
- **H — Hand off with rights:** source license + engine terms (Firefly indemnification vs FLUX
  outputs-vs-service) + disclosure labels; master as PNG/TIFF → WoopSocial.

## The reality (verify-quarterly)
2026 editing: backg