Room makeover preview
Preview a room style change 從 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
建立 repaired image 從 broken image, using a task-first 工作流 instead of a loose 提示詞 dump.
inpainting, detailer
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: 修復 hands 和 faces
場景: 修復與編輯 / 修復 failures
輸入: broken image
輸出: repaired image
Tools: ADetailer, Impact Pack, GPT Image 2
Example 輸入: Product image: generated bottle 視覺 使用 warped label edge
Issue to fix: distorted 標籤文字 和 uneven cap 形狀
Must preserve: composition, lighting, product 顏色, 材質
Edit scope: repair only the broken areas
Do not change: 聲明, logo, flavor, size, 或 packaging structure
品質檢查: the result must match the promised 輸出 和 preserve the user intent.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
建立 repaired image 用於 this task: 修復 common AI portrait failures
輸入 available: broken image
Example 輸入: Product image: generated bottle 視覺 使用 warped label edge
Issue to fix: distorted 標籤文字 和 uneven cap 形狀
Must preserve: composition, lighting, product 顏色, 材質
Edit scope: repair only the broken areas
Do not change: 聲明, logo, flavor, size, 或 packaging structure
Preferred tool path: ADetailer, Impact Pack, GPT Image 2
Keep the result faithful to the 輸入 和 optimize 用於 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 從 a photo
轉換 a 產品照片 into a premium ad scene
替換 或 generate 產品背景s while preserving product