Photoreal FACS Expression Grid

Photoreal FACS Expression Grid

原始文档

GPT Image 2 · en

Using REFERENCE_0 and REFERENCE_1 as the FACS action-unit guide, create a photorealistic expression-control test sheet instead of an illustrated chart. Generate {argument name="grid layout" default="15 panels arranged in 3 rows and 5 columns"} showing the same {argument name="subject" default="realistic young female student"} repeated in every panel with identical framing, lighting, hairstyle, and {argument name="outfit" default="white school shirt with a gray ribbon tie"}. Apply a different subtle facial-expression change to each panel based on these {argument name="FACS action units" default="AU1, AU2, AU4, AU5, AU6, AU7, AU9, AU10, AU12, AU15, AU17, AU20, AU23, AU24, AU25"}, while preserving identity consistency and keeping the changes limited to the face. Use a close-up front-facing portrait crop from upper chest to top of head, natural outdoor backlight, shallow depth of field, and thin white dividers between panels. Do not include any chart titles, labels, AU text, explanations, or Japanese text.

使用方法

  1. 复制完整原始提示词,并保留其中的参数。
  2. 按需求替换主体、文字和构图要求。
  3. 在兼容的外部工具中使用,核对当前使用条件并检查结果。

开始前需了解

  • 先确认是否需要参考图。标注兼容模型,不代表该示例由这个模型生成。
  • 核对名称、数字与画面文字;不同模型版本的结果可能不同。

相似案例

Product Marketing - Multi-Expression Sliced Fashion Poster
Nano Banana Proen

Create a {argument name="style" default="luxury fashion editorial poster"} based on my reference image. Preserve the exact facial identity, hairstyle, facial structure, skin tone, and overall appearance of the reference person. The portrait is divided into {argument name="layout

Photoreal Schoolgirl Shrine Portrait
GPT Image 2en

A realistic half-length portrait, the subject being a{argument name="subject" default="young women"} Standing in bright natural sunlight, the photo is taken in a vertical format. She has long, straight hair.{argument name="hair color" default="Dark brown"} Her hair, glossy and lu

4-Panel Professional Avatar Grid
GPT Image 2en

{ "type": "2x2 portrait grid", "subject": "{argument name=\"subject description\" default=\"A young East Asian man with short black hair and a smile.\"}", "style": "Photorealistic rendering, high resolution, professional lighting, and consistent facial features across all p

FACS Expression Portrait Matrix
GPT Image 2en

{ "objective": "Create a 3x3 portrait collage inspired by expressive fashion photography, using FACS (Facial Action Coding System) to define each facial expression. The subject is an {argument name="subject" default="extremely beautiful redhead woman with green eyes"}, captured

Cherry Blossom Kimono Portrait Grid
GPT Image 2en

{ "type": "Edit portrait collage", "subject": { "gender_presentation": "young women", "hair": { "color": "Dark brown", "style": "Short straight bob, chin length, side part" }, "wardrobe": { "main_garment": "A light-colored traditional kimono