Auto-sync: 2026-04-26 04:02
This commit is contained in:
39
wiki/entities/Gemini.md
Normal file
39
wiki/entities/Gemini.md
Normal file
@@ -0,0 +1,39 @@
|
||||
---
|
||||
title: "Gemini API"
|
||||
type: entity
|
||||
tags: ["google", "image-generation", "ai", "gemini", "carousel"]
|
||||
sources: ["marketing-carousel-growth-engine"]
|
||||
last_updated: 2026-04-26
|
||||
---
|
||||
|
||||
## Definition
|
||||
|
||||
Google 的多模态 AI 模型 API,支持文本和图像生成。在 [[marketing-carousel-growth-engine]] 中用于生成 TikTok/Instagram 轮播图。
|
||||
|
||||
## Key Details
|
||||
|
||||
- **Model**: `gemini-3.1-flash-image-preview`
|
||||
- **API**: Google Generative Language API
|
||||
- **Credential**: `GEMINI_API_KEY` 环境变量(免费层可用)
|
||||
- **Key**: https://aistudio.google.com/app/apikey
|
||||
|
||||
## Usage in Carousel Growth Engine
|
||||
|
||||
- **Slide 1**: 纯文本 prompt 生成首张幻灯片,定义视觉 DNA
|
||||
- **Slides 2-6**: 图生图模式,以 slide-1.jpg 作为 `--input-image` 参考输入,保持视觉连贯性
|
||||
- **Output**: 768x1376 (9:16) JPG 格式轮播图
|
||||
- **Script**: `generate-slides.sh` 编排管道,`generate_image.py`(Python via `uv`)调用 API
|
||||
|
||||
## 技术规格
|
||||
|
||||
| 参数 | 值 |
|
||||
|------|-----|
|
||||
| 分辨率 | 768×1376 (9:16 竖版) |
|
||||
| 格式 | JPG(TikTok 拒绝 PNG) |
|
||||
| 视觉连贯性 | 第一张定义 DNA,后续图生图 |
|
||||
| 免费层 | 可用(需 Google AI Studio API Key) |
|
||||
|
||||
## Aliases
|
||||
- Gemini
|
||||
- Google Gemini
|
||||
- Gemini 3.1 Flash Image
|
||||
Reference in New Issue
Block a user