Room makeover preview
Preview a room style change 从 a photo
修复 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
创建 repaired image 从 broken image, using a task-first 工作流 instead of a loose 提示词 dump.
inpainting, detailer
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: 修复 hands 和 faces
场景: 修复与编辑 / 修复 failures
输入: broken image
输出: repaired image
Tools: ADetailer, Impact Pack, GPT Image 2
Example 输入: Product image: generated bottle 视觉 使用 warped label edge
Issue to fix: distorted 标签文字 和 uneven cap 形状
Must preserve: composition, lighting, product 颜色, 材质
Edit scope: repair only the broken areas
Do not change: 声明, logo, flavor, size, 或 packaging structure
质量检查: the result must match the promised 输出 和 preserve the user intent.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
创建 repaired image 用于 this task: 修复 common AI portrait failures
输入 available: broken image
Example 输入: Product image: generated bottle 视觉 使用 warped label edge
Issue to fix: distorted 标签文字 和 uneven cap 形状
Must preserve: composition, lighting, product 颜色, 材质
Edit scope: repair only the broken areas
Do not change: 声明, logo, flavor, size, 或 packaging structure
Preferred tool path: ADetailer, Impact Pack, GPT Image 2
Keep the result faithful to the 输入 和 optimize 用于 the 修复 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 从 a photo
转换 a 产品照片 into a premium ad scene
替换 或 generate 产品背景s while preserving product