This is not a prompt itself, but a meta-prompting strategy designed to prevent image generation failures due to triggering Google Nano Banana Pro's safety filters (Safety Filter/Risk Control). It instructs the model to automatically filter dangerous words, use safe alternatives, and ensures the generated prompt meets platform requirements. It also lists explicitly forbidden categories and mandatory safe replacement words that must be included in every prompt.
应用现在能够自动过滤所有危险词汇,使用安全替代词,并确保生成的提示词符合平台风控要求
绝对禁止的词汇:
类别禁用词汇
能量/特效lightning, electric, energy, spark, voltage, current
战斗/冲突attack, battle, fight, punch, kick, strike, combat, clash
危险元素fire, flame, explosion, weapon, sword, knife, gun
负面情绪fierce, intense, aggressive, violent, rage, angry, scream, panic
身体恐怖glowing eyes, red eyes, blood, wound, transform, distort
强制使用的安全替代词
原词替代词
lightning/electricsoft light, warm light, ambient light
fight/attackmove toward, approach, interaction
fierce/intensewarm, calm, gentle, peaceful
explosion/firebloom, brighten, illuminate, radiate
angry/rageconcerned, surprised, amazed, excited
每个提示词必须包含至少2个安全词汇
gentle, soft, calm, peaceful, warm, bright, smooth, quiet, serene, beautiful, lovely, sweet, slowly, smoothly, gracefullyCC BY 4.0. Prompt pages keep the original attribution and source links from the upstream gallery records stored in the database.


