Personal avatar set 從 one photo
建立 multiple avatar styles 從 one portrait
建立 a profile 或 community banner 從 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
建立 banner image 從 text brief, using a task-first 工作流 instead of a loose 提示詞 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 從 a theme
場景: 生活 / Social sharing covers
輸入: text brief
輸出: banner image
Tools: FLUX, GPT Image 2, ComfyUI
Example 輸入: Input: text brief
Goal: describe the target channel, audience, style, 和 non-negotiable details.
Constraints: list what must stay unchanged 和 what can be creatively changed.
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 banner image 用於 this task: 建立 a profile 或 community banner 從 a mood
輸入 available: text brief
Example 輸入: Input: text brief
Goal: describe the target channel, audience, style, 和 non-negotiable details.
Constraints: list what must stay unchanged 和 what can be creatively changed.
Preferred tool path: FLUX, GPT Image 2, ComfyUI
Keep the result faithful to the 輸入 和 optimize 用於 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.
使用 when the image is close but facial details, hands, 或 small identity cues need repair.
Open workflow使用 model-flexible 提示詞 structures before opening a full portrait 工作流.
Open workflow使用 the full 庫 when the job moves 從 portrait generation into covers, banners, 或 format changes.
Open workflow建立 multiple avatar styles 從 one portrait
轉換 a casual photo into polished profile options
建立 movie-poster style portraits 從 one face