同一角色在同一页上有八个分镜,附有字幕、镜头运动箭头和平面图。

GPT-Image-2 · @FlyAIgh · Fri Sep 18

在画廊中打开

分享链接 · https://openimages.ajiang.me/p/2100974843441389851/

同一角色在同一页上有八个分镜,附有字幕、镜头运动箭头和平面图。 GPT Image 2 对比 2.5,样本 05:一份故事板。角色是 SUMI,由 FlyAIgh 内部设计的原创…
color_palette · warm-tonescomposition · medium-shotcomposition · multi-panelhuman_attributes · long-hairlighting · side-litmood · tense

提示词(原文,逐字保留)

Eight shots of one character on a single page, with captions, camera arrows and a floor plan. GPT Image 2 vs 2.5, specimen 05: a storyboard sheet. The character is SUMI, an original character FlyAIgh designed in-house. Not a real person. Three reference images of her went in. She fights three helmeted couriers in the corridor of a sleeper carriage. The prompt asks for a header, eight shots with a caption each (lens, camera move, duration, action, dialogue), camera-move arrows, a light shift from warm corridor lamps to tunnel light to a cold platform, and a footer floor plan with five compartments, movement paths for SUMI and couriers C1 to C3, and four camera wedges. Same prompt and references, one run each, first result kept. GPT Image 2 at High, 2.5 Sunburst and 2.5 Flare at Max, all 4K. All three: SUMI is the only silver-haired figure on the sheet, eight shots, header present, every dialogue line correct. Where they differ is the floor plan and the captions: GPT Image 2 draws four compartments and labels the couriers C1, C2, C2, C3. C2 appears twice. Sunburst draws all five compartments and labels them COMP 1 to COMP 5. The prompt did not ask for those labels. Flare draws four compartments, labelled COMPARTMENT 1, 2, 3 and 5. Its caption for shot 7E reads "Two turrs of chain" where the prompt says "turns". No winner called. A 100% crop of shots 7G and 7H from each sheet is in the image. Method and what you pay in the reply.

中文译文

同一角色在同一页上有八个分镜,附有字幕、镜头运动箭头和平面图。 GPT Image 2 对比 2.5,样本 05:一份故事板。角色是 SUMI,由 FlyAIgh 内部设计的原创角色,非真人。输入了她的三张参考图。她在卧铺车厢的走廊中与三名戴头盔的信使战斗。提示词要求包含:一个页眉、八个分镜(每个分镜配一段字幕,内容包括镜头、运动方式、时长、动作、对白)、镜头运动箭头、灯光从温暖的车厢灯转为隧道光再转为冷色调站台,以及页脚的一张平面图,包含五个隔间、SUMI 与信使 C1 至 C3 的运动路径、四个机位楔形标记。相同的提示词与参考图,各运行一次,保留第一次结果。GPT Image 2 使用 High,2.5 Sunburst 与 2.5 Flare 使用 Max,均为 4K。 三者共通点:SUMI 是画面上唯一的银发人物;八张分镜齐全;页眉存在;每条对白都正确。 它们的差异集中在平面图与字幕: GPT Image 2 画出四个隔间,并将信使标注为 C1、C2、C2、C3。C2 出现了两次。 Sunburst 画出全部五个隔间,并将其标注为 COMP 1 至 COMP 5。提示词并未要求这些标注。 Flare 画出四个隔间,标注为 COMPARTMENT 1、2、3 和 5。镜头 7E 的字幕写作 "Two turrs of chain",而提示词原文为 "turns"。 不评判胜负。图中包含每张故事板 7G 与 7H 镜头的 100% 裁切图。请在回复中说明方法及所付出的成本。

来源与署名

原文由 @FlyAIgh 发布在 X:查看原推文。 本页逐字保留原文并提供机器翻译的中文解读;版权归原作者所有。

在画廊中浏览

同工具的更多提示词