Image prompt
Generates a minimally altered version of a reference character image with a specified FACS-based facial expression change while preserving the original look and composition.
Copy directly into the target model and adjust for your input assets.
Using the provided reference image as the character base, keep the same chibi 3D figure, outfit, hairstyle, lighting, plain white background, and overall composition unchanged, but modify only the facial expression according to FACS action units: {argument name="FACS action units" default="AU1C + AU2C + AU5D + AU26C"}. Preserve the reference image’s square face-obscuring block in the same central position and regenerate the image cleanly with the same toy-like render quality.
Original source details are kept for attribution and review.
GitHub source：YouMind-OpenLab/gpt-image-2-prompts-search
This page is adapted from YouMind OpenLab GitHub prompt libraries. License: MIT。