Room makeover preview
Preview a room style change から a photo
修復 common AI portrait failures
Use this skill when you need a repeatable image workflow, not a one-off prompt guess. It defines the input, output, tool path, and quality gate before generation starts.
High-intent repair page
作成 repaired image から broken image, using a task-first ワークフロー instead of a loose プロンプト dump.
inpainting, detailer
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: 修正 hands と faces
シーン: 修正と編集 / 修復 failures
入力: broken image
出力: repaired image
Tools: ADetailer, Impact Pack, GPT Image 2
Example 入力: Product image: generated bottle ビジュアル で warped label edge
Issue to fix: distorted ラベル文字 と uneven cap 形状
Must preserve: composition, lighting, product 色, 素材
Edit scope: repair only the broken areas
Do not change: 訴求, logo, flavor, size, または packaging structure
品質チェック: the result must match the promised 出力 と preserve the user intent.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
作成 repaired image 向け this task: 修復 common AI portrait failures
入力 available: broken image
Example 入力: Product image: generated bottle ビジュアル で warped label edge
Issue to fix: distorted ラベル文字 と uneven cap 形状
Must preserve: composition, lighting, product 色, 素材
Edit scope: repair only the broken areas
Do not change: 訴求, logo, flavor, size, または packaging structure
Preferred tool path: ADetailer, Impact Pack, GPT Image 2
Keep the result faithful to the 入力 と optimize 向け the 修復 failures scene.
Use these routes when the next user question shifts from this workflow into background replacement, product repair, ad variants, listing review, or prompt examples.
Preview a room style change から a photo
変換 a 商品写真 into a premium ad scene
置き換え または generate 商品背景s while preserving product