# GPT Image Hub prompt

## 並排模型架構對比資訊圖
- URL: https://www.gptimagehub.com/zh-TW/library/side-by-side-model-architecture-comparison-infographic
- Generator URL: https://www.gptimagehub.com/zh-TW/generate?promptId=oss-ym-g2-15614
- Markdown URL: https://www.gptimagehub.com/api/agent/markdown?path=%2Fzh-TW%2Flibrary%2Fside-by-side-model-architecture-comparison-infographic
- Category: 資訊圖與教育
- Model: gpt-image-2
- Aspect ratio: 2:1
- Style: graphic-design
- Tags: 資訊圖, 技術圖表, 架構, 對比圖, 簡報投影片, transformer
- Updated: 2026-10-27T13:35:53.098Z
- Created: 2026-10-27T13:35:53.098Z

生成用於技術展示的兩大模型架構並排對比圖。可透過修改括號內的模型名稱、參數量與層維度進行自訂。

### Full prompt
```text
{"type":"並排式AI模型架構對比資訊圖","style":"整潔的技術架構圖、白底、細黑色輪廓線、圓角矩形、虛線標註框、顏色高亮、簡報幻燈片美學、向量資訊圖","canvas":{"aspect_ratio":"2:1","resolution":"wide horizontal"},"title_row":{"left_title":"[DeepSeek V3/R1 (671 billion)]","right_title":"[DeepSeek V4 (1.2 trillion)]","left_title_color":"亮橙紅色","right_title_color":"鮮藍色"},"layout":{"columns":2,"sections":[{"title":"[DeepSeek V3/R1 (671 billion)]","position":"左半部","count":9,"labels":["Vocabulary size of 129k","FeedForward (SwiGLU) module","Intermediate hidden layer dimension of 2,048","MoE layer","Supported context length of 128k tokens","First 3 blocks use dense FFN with hidden size 18,432 instead of MoE","Sample input text","Embedding dimension of 7,168","128 heads"]},{"title":"[DeepSeek V4 (1.2 trillion)]","position":"右半部","count":9,"labels":["Vocabulary size of 160k","FeedForward (SwiGLU) module","Intermediate hidden layer dimension of 3,072","MoE layer","Supported context length of 256k tokens","First 3 blocks use dense FFN with hidden size 24,576 instead of MoE","Sample input text","Embedding dimension of 8,192","128 heads"]},{"title":"底部對比表格","position":"底部全寬","count":10,"labels":["Total parameters","Active parameters per token","Hidden size","Intermediate (FF)","Attention heads","Context length","Embedding dimension","Vocabulary size"]}]},"left_panel":{"background":"極淺灰色圓角矩形","main_stack":{"count":8,"blocks":["Tokenized text","Token embedding layer","RMSNorm 1","Multi-head Latent Attention","RMSNorm 2","MoE","Final RMSNorm","Linear output layer"]},"side_module":"左側注意力模組附帶RoPE","attention_block":{"label":"Multi-head Latent Attention","accent":"Latent字樣使用橙紅色"},"feedforward_inset":{"title":"FeedForward (SwiGLU) module","count":4,"blocks":["Linear layer","SiLU activation","Linear layer","Linear layer"],"diagram":"雙分支相乘後投影"},"moe_inset":{"title":"MoE layer","count":5,"blocks":["top combine node","Feed forward","Feed forward","Router","expert count badge 256"],"details":"代表1個選中專家的黑色小方塊、指向專家層的向上箭頭、虛線分隔線"},"annotations":{"vocab":"Vocabulary size of 129k","ff_dim":"Intermediate hidden layer dimension of 2,048","context":"Supported context length of 128k tokens","dense_first_blocks":"First 3 blocks use dense FFN with hidden size 18,432 instead of MoE","resource_savings":"Resource savings: Model size is 671B but only 1 (shared) + 8 experts active per token; only 37B parameters are active per inference step"},"bottom_stats":{"count":8,"items":["Total parameters: 671B","Active parameters per token: 37B (1 + 8 experts)","Hidden size: 7,168","Intermediate (FF): 2,048","Attention heads: 128","Context length: 128k","Embedding dimension: 7,168","Vocabulary size: 129k"]}},"right_panel":{"background":"極淺藍色圓角矩形","main_stack":{"count":8,"blocks":["Tokenized text","Token embedding layer","RMSNorm 1","Multi-head Latent Attention","RMSNorm 2","MoE","Final RMSNorm","Linear output layer"]},"side_module":"左側注意力模組附帶RoPE","attention_block":{"label":"Multi-head Latent Attention","accent":"Latent字樣使用藍色"},"feedforward_inset":{"title":"FeedForward (SwiGLU) module","count":4,"blocks":["Linear layer","SiLU activation","Linear layer","Linear layer"],"diagram":"與左側結構相同"},"moe_inset":{"title":"MoE layer","count":5,"blocks":["top combine node","Feed forward","Feed forward","Router","expert count badge 384"],"details":"代表1個選中專家的黑色小方塊、指向專家層的向上箭頭、虛線分隔線、藍色邊框強調"},"annotations":{"vocab":"Vocabulary size of 160k","ff_dim":"Intermediate hidden layer dimension of 3,072","context":"Supported context length of 256k tokens","dense_first_blocks":"First 3 blocks use dense FFN with hidden size 24,576 instead of MoE","resource_savings":"Resource savings: Model size is 1.2T but only 1 (shared) + 8 experts active per token; only 52B parameters are active per inference step"},"bottom_stats":{"count":8,"items":["Total parameters: 1.2T","Active parameters per token: 52B (1 + 8 experts)","Hidden size: 8,192","Intermediate (FF): 3,072","Attention heads: 128","Context length: 256k","Embedding dimension: 8,192","Vocabulary size: 160k"]}},"global_notes":"生成高度對稱的超詳細Transformer模型架構對比圖。左右各包含一個完整模型堆疊以及2個內嵌結構圖（前饋模組與MoE專家層）。模組間附帶連線箭頭、細小技術文字與指引線。保持密集專業的幻燈片排版風格，左側使用橙紅色強調，右側使用藍色強調，底部附帶橫跨全寬的資料對比表。"}
```