Room makeover preview
Preview a room style change 에서 a photo
수정 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
만들기 repaired image 에서 broken image, using a task-first 워크플로 instead of a loose 프롬프트 dump.
inpainting, detailer
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: 고치기 hands 및 faces
장면: 수정 및 편집 / 수정 failures
입력: broken image
출력: repaired image
Tools: ADetailer, Impact Pack, GPT Image 2
Example 입력: Product image: generated bottle 비주얼 로 warped label edge
Issue to fix: distorted 라벨 텍스트 및 uneven cap 형태
Must preserve: composition, lighting, product 색상, 소재
Edit scope: repair only the broken areas
Do not change: 주장, logo, flavor, size, 또는 packaging structure
품질 확인: the result must match the promised 출력 및 preserve the user intent.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
만들기 repaired image 용 this task: 수정 common AI portrait failures
입력 available: broken image
Example 입력: Product image: generated bottle 비주얼 로 warped label edge
Issue to fix: distorted 라벨 텍스트 및 uneven cap 형태
Must preserve: composition, lighting, product 색상, 소재
Edit scope: repair only the broken areas
Do not change: 주장, logo, flavor, size, 또는 packaging structure
Preferred tool path: ADetailer, Impact Pack, GPT Image 2
Keep the result faithful to the 입력 및 optimize 용 the 수정 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 에서 a photo
변환 a 제품 사진 into a premium ad scene
교체 또는 generate 제품 배경s while preserving product