修正と編集

Change image format

Essential

Expand image into banner

Extend an image into website または social banner

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.

入力

元画像

出力

banner image

このスキルを使うコピー形式

Best fit

Change image format

ComfyUI inpaintingFLUXGPT Image 2

Practical format-conversion ワークフロー向け web と social publishing

Job to be done

作成 banner image から元画像, using a task-first ワークフロー instead of a loose プロンプト dump.

Workflow type

outpainting, upscale

Quality promise

The output must preserve user intent, survive visual inspection, and be ready for the target channel.

Workflow outline

Prepare the source 入力: 元画像.
Pick a first tool path: ComfyUI inpainting, FLUX, GPT Image 2.
生成または edit toward the promised deliverable: banner image.
Review the image 向け drift, broken details, unreadable text, と weak composition.
保存 the プロンプト, references, と final settings that produced the best reusable result.

Copy-ready skill card

Skill: Expand image into banner

シーン: 修正と編集 / Change image format

入力: 元画像

出力: banner image

Tools: ComfyUI inpainting, FLUX, GPT Image 2

Example 入力: Input: 元画像

Goal: describe the target channel, audience, style, と non-negotiable details.

Constraints: list what must stay unchanged と what can be creatively changed.

品質チェック: the result must match the promised 出力と preserve the user intent.

Branch logic

If the user has not provided 元画像, ask 向け it before generating the final banner image.
If a reference image is provided, preserve the subject identity, proportions, と important details before changing style または scene.
If the first result fails ビジュアル inspection, fix the smallest broken area first instead of regenerating the whole image.
If the first tool path fails, switch to the next listed option: FLUX, GPT Image 2.

When not to use

Do not use this as proof that the generated banner image is factually real または legally approved.
Do not use it when the user needs professional legal, medical, safety, または regulated-compliance judgment.

Copy distribution

Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.

Quality gate

The final asset clearly matches the requested banner image.
The main subject still reflects the original 元画像.
Text, hands, logos, edges, と商品ディテール are not visibly broken.
The result is usable in the target channel 変更せずに another full regeneration.

Prompt starter

作成 banner image 向け this task: Extend an image into website または social banner

入力 available: 元画像

Example 入力: Input: 元画像

Goal: describe the target channel, audience, style, と non-negotiable details.

Constraints: list what must stay unchanged と what can be creatively changed.

Preferred tool path: ComfyUI inpainting, FLUX, GPT Image 2

Keep the result faithful to the 入力と optimize 向け the change image format scene.

Evidence and maintenance

Source IDs

IMG-018, IMG-023, IMG-026, IMG-049

Priority

Essential

Library track

Starter

Related intent routes

Related workflows by search intent

Use these routes when the next user question shifts from this workflow into background replacement, product repair, ad variants, listing review, or prompt examples.

Prompt examples

Get プロンプト starters