Lab / Multi-Ref Modes / 2-Ref Scene + Character Composition

2-Ref Scene + Character Composition

1 场景 ref + 1 角色 ref → 角色置入场景 · 场景 1:1 复刻 + 角色 identity 锁

1996 春节 + yuan_kid 真儿童 ref · OpenAI minor filter 通过

observed_once · ¥0.5 · aspect 1:1 · providers · gpt_image_2 · id · multiref-2ref-scene-character

sample · projects/yuan_kid_history_test_v1/step1_yuan_kid_1996_v1.png

prompt not yet extracted to library

Verbatim prompt lives in the experiment script. Pending migration to recipes/image_gen/gpt_image_2/prompts/.

Cross-Reference

methodology · — no dedicated recipe doc · referenced in memory only —

axis · §Multi-Ref Modes · image_urls 编辑模式 · ref-driven generation

used in works · yuan_kid_history_test_v1