Personal avatar set から one photo
作成 multiple avatar styles から one portrait
作成 a profile または community banner から a mood
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.
Can link to outpainting
作成 banner image から text brief, using a task-first ワークフロー instead of a loose プロンプト dump.
text-to-image, outpainting
The output must preserve user intent, survive visual inspection, and be ready for the target channel.
Skill: Personal social banner から a theme
シーン: 生活 / Social sharing covers
入力: text brief
出力: banner image
Tools: FLUX, GPT Image 2, ComfyUI
Example 入力: Input: text brief
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.
Take this skill into your AI tool as a prompt, a workflow card, or a portable SKILL.md draft.
作成 banner image 向け this task: 作成 a profile または community banner から a mood
入力 available: text brief
Example 入力: Input: text brief
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: FLUX, GPT Image 2, ComfyUI
Keep the result faithful to the 入力 と optimize 向け the social sharing covers 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.
使う when the image is close but facial details, hands, または small identity cues need repair.
Open workflow使う model-flexible プロンプト structures before opening a full portrait ワークフロー.
Open workflow使う the full ライブラリ when the job moves から portrait generation into covers, banners, または format changes.
Open workflow作成 multiple avatar styles から one portrait
変換 a casual photo into polished profile options
作成 movie-poster style portraits から one face