怎么填变量：[Transformer 结构] 可换成你要讲的结构，同时把下面的模块列表一起改，例如"ResNet 残差块""U-Net 编码解码""Vision Transformer 图像分块"；[顶会论文终稿] 可写"期刊黑白印刷""技术博客扁平风"；[论文出处] 写原论文简称和年份即可。示例图是英文标签版：左边蓝色"ENCODER (×N)"、右边绿色"DECODER (×N)"，每个子层是浅色圆角块，残差箭头和"keys, values"交叉箭头都画出来了，标题和副标题在最上方。

常见问题与调整：

• 箭头连错或多出模块：把模块列表写成编号清单，并加"只画列出的模块，不要额外添加"。
• 中文标签挤在一起：改短标签，如"自注意力""前馈"，或保留英文标签。
• 想要黑白印刷版：加"灰度配色，只用线型和灰度区分模块"。
• 想要竖版放进 PPT 一侧：画幅改成 3:4，两栏改为上下排列。

适合：组会 / 课程 PPT、技术博客配图、论文草图底稿；不适合未经核对直接作为正式投稿插图。

英文原版

Landscape 16:9 academic concept figure of the Transformer encoder-decoder architecture, NeurIPS camera-ready style. Two vertical column stacks side-by-side with a dashed divider.

LEFT column header: "ENCODER (×N)". Blocks bottom-to-top: "Input tokens" → "Input Embedding" → "+ Positional Encoding" → dashed "Encoder layer" containing "Multi-Head Self-Attention", "Add & Norm", "Feed-Forward", "Add & Norm", with thin curved residual arrows around each sublayer.

RIGHT column header: "DECODER (×N)". Blocks bottom-to-top: "Output tokens (shifted right)" → "Output Embedding" → "+ Positional Encoding" → dashed "Decoder layer" containing "Masked Multi-Head Self-Attention", "Add & Norm", "Multi-Head Cross-Attention" (horizontal arrow from encoder top labeled "keys, values"), "Add & Norm", "Feed-Forward", "Add & Norm". Above decoder: "Linear", "Softmax", "Output probabilities".

Title: "Transformer: encoder–decoder with multi-head attention". Subtitle: "Vaswani et al., 2017".

改编自 wuyoscar/GPT-Image2-Skill 收录的提示词（仓库整理），许可证 MIT（Copyright (c) 2026 Wuyoscar）。