角色表+场景板钉死:Seedance 最多 50 参考
先钉角色表与 location plate,再写戏;Seedance 2.5 可吃到约 50 张参考。写实多角戏的防漂配方。
演示视频
原帖未提供效果图
提示词
#9/10 · GPT Image 2.5 + Seedance 2.5 · photoreal scene, reference-map structure 4/ Seedance 2.5 i made this in @dreamina_ai #DreaminaCPP' pin both character sheets and the location plate women standing image as references first, then write. it takes up to 50 references and generates with sound in the same pass. structure that actually works: === REFERENCE MAP === [LOCATION REF] → the courtyard archway scene: the woman at frame right in the rust terracotta wrap top with the raffia belt, the second woman in the green silk blouse further back near the stone fountain, the bougainvillea overhead, the whitewashed cliffside town, the sea and the low sun beyond. This is the exact first frame of the clip and the room, light and camera look for the whole take. [WOMAN REF] → face and identity only. Eyes bare, no glasses. [MAN REF] → face and identity only. Eyes bare, no glasses. === CHARACTER ELEMENT === [MAN] → man, mid to late 20s, olive tan skin, dark brown wavy hair swept back off the forehead, thick dark eyebrows, warm brown eyes, short trimmed beard, strong jawline, easy natural smile. Identity from [MAN REF] only. Wardrobe is new, not taken from any reference image: an open collar off white linen shirt, top two buttons undone, no undershirt, sleeves rolled loosely to mid forearm, tucked into tailored charcoal linen trousers, a thin gold chain barely visible at the open collar. He does not film and never holds the camera. He comes from the right side of the courtyard, from near the potted olive trees, and goes after her to the left. [… trimmed — full version in the original post] — prompt & video by @abxxai
中文译文
#9/10 · GPT Image 2.5 + Seedance 2.5 · 照片级写实场景,参考图映射结构 4/ Seedance 2.5 我在 @dreamina_ai #DreaminaCPP' 里做的这个 先把角色设定图和场景板里那张女性站立的图像都固定为参考,然后再写提示词。它最多支持 50 张参考图,并在同一次生成中带声音输出。 真正有效的结构: === REFERENCE MAP === [LOCATION REF] → 庭院拱门场景:画面右侧的女性穿着铁锈赤陶色裹身衫,系酒椰叶纤维腰带;更靠后、在石喷泉附近的第二位女性穿着绿色丝绸衬衫;头顶是三角梅;远处是白墙悬崖小镇、大海和低垂的太阳。这就是片段的准确首帧,也是整条镜头中房间、光线和摄影机的观感。 [WOMAN REF] → 仅脸部和身份。露出眼睛,不戴眼镜。 [MAN REF] → 仅脸部和身份。露出眼睛,不戴眼镜。 === CHARACTER ELEMENT === [MAN] → 男性,25 岁上下到接近 30 岁,橄榄色偏深肤色,深棕色波浪发向后梳、露出额头,浓密深色眉毛,温暖的棕色眼睛,修剪整齐的短胡须,硬朗的下颌线,自然轻松的微笑。身份仅取自 [MAN REF]。服装是全新的,不取自任何参考图:开领米白色亚麻衬衫,最上面两颗纽扣解开,内无打底衫,袖子松松挽到前臂中部,下摆塞进合身的炭灰色亚麻长裤,开领处隐约可见一条细金链。他不拍摄,也从不掌机。他从庭院右侧走来,从盆栽橄榄树附近过来,随后向左追向她。 [… 已截断 — 完整版本见原帖] — 提示词与视频 by @abxxai
溯源
- 原作者
- kayforkind
- 发布日期
- 2026-09-14
- 原始出处
- 查看原帖 ↗
- 收录来源
- xianyu110/awesome-gpt-image2.5 · 2099391447128518810 · MIT