合并豆包万相图片技能到image-tools，删除doubao-image独立目录
This commit is contained in:
12600k-rog-d4
@@ -1,17 +1,193 @@
|
||||
---
|
||||
name: image-tools
|
||||
description: 阿里云万相2.7图生图工具，用于AI生成产品主图、场景图、电商素材。Invoke when user needs to generate product images, e-commerce visuals, or AI image editing.
|
||||
description: AI图片生成与编辑工具集。包含豆包万相（Doubao Seedream）和阿里云万相2.7两个AI图片引擎，支持文生图、图生图、多图融合、图片编辑。用于生成产品主图、场景图、电商素材、宣传页等。Invoke when user needs to generate, edit, or transform images for e-commerce or product visuals.
|
||||
---
|
||||
|
||||
# Image Tools - 万相2.7 AI图生图
|
||||
# Image Tools - AI图片生成与编辑工具集
|
||||
|
||||
使用阿里云百炼 **wan2.7-image-pro** 模型进行 AI 图生图处理，支持文生图、图生图、图片编辑。
|
||||
集成两个AI图片引擎：
|
||||
1. **豆包万相（Doubao Seedream）** — 火山引擎Ark API，支持文生图、图生图、多图融合、图片编辑、批量生成
|
||||
2. **阿里云万相2.7** — 阿里云百炼 wan2.7-image-pro，支持文生图、图生图、图片编辑
|
||||
|
||||
## 前提条件
|
||||
---
|
||||
|
||||
## 引擎1：豆包万相（Doubao Seedream）
|
||||
|
||||
使用火山引擎 Ark API 的 Doubao Seedream 模型，支持文生图、图生图、多图融合、图片编辑。
|
||||
|
||||
### 前提条件
|
||||
|
||||
- `curl.exe`（Windows内置）
|
||||
- Ark API Key: `ark-119a37ed-f123-42fc-aea6-b38d47d47fc0-f7ddf`
|
||||
- API端点: `https://ark.cn-beijing.volces.com/api/v3/images/generations`
|
||||
|
||||
### 模式一览
|
||||
|
||||
| 模式 | `image`参数 | 用途 |
|
||||
|---|---|---|
|
||||
| 文生图 | 省略或`[]` | 从文字描述生成图片 |
|
||||
| 图生图 | `["url1"]` | 风格转换、精修、变换 |
|
||||
| 多图融合 | `["url1","url2",...]` | 最多14张参考图融合 |
|
||||
| 图片编辑 | `["url1"]` + 编辑提示词 | 移除/替换元素、换背景等 |
|
||||
|
||||
默认模型: `doubao-seedream-5-0-260128`
|
||||
|
||||
### 文生图（Windows PowerShell）
|
||||
|
||||
```powershell
|
||||
$tmpFile = "$env:TEMP\request.json"
|
||||
$prompt = "YOUR_PROMPT_HERE"
|
||||
$json = @"
|
||||
{"model":"doubao-seedream-5-0-260128","prompt":"$prompt","size":"2k","sequential_image_generation":"disabled","response_format":"url","stream":false,"watermark":false}
|
||||
"@
|
||||
$sw = [System.IO.StreamWriter]::new($tmpFile, $false, (New-Object System.Text.UTF8Encoding $false))
|
||||
$sw.Write($json); $sw.Close()
|
||||
|
||||
$response = curl.exe -s -X POST https://ark.cn-beijing.volces.com/api/v3/images/generations `
|
||||
-H "Content-Type: application/json" `
|
||||
-H "Authorization: Bearer ark-119a37ed-f123-42fc-aea6-b38d47d47fc0-f7ddf" `
|
||||
-d "@$tmpFile" | ConvertFrom-Json
|
||||
|
||||
$imageUrl = $response.data[0].url
|
||||
$outputPath = Join-Path (Get-Location) "output-name.png"
|
||||
curl.exe -s -o $outputPath $imageUrl
|
||||
Write-Output $outputPath
|
||||
```
|
||||
|
||||
### 图生图/图片编辑（本地文件输入，Windows PowerShell）
|
||||
|
||||
```powershell
|
||||
$imgBytes = [System.IO.File]::ReadAllBytes((Resolve-Path "path\to\input.png"))
|
||||
$imgBase64 = [System.Convert]::ToBase64String($imgBytes)
|
||||
|
||||
$tmpFile = "$env:TEMP\request.json"
|
||||
$prompt = "YOUR_EDIT_INSTRUCTIONS_HERE"
|
||||
$json = @"
|
||||
{"model":"doubao-seedream-5-0-260128","prompt":"$prompt","image":["data:image/png;base64,$imgBase64"],"size":"2k","sequential_image_generation":"disabled","response_format":"url","stream":false,"watermark":false}
|
||||
"@
|
||||
$sw = [System.IO.StreamWriter]::new($tmpFile, $false, (New-Object System.Text.UTF8Encoding $false))
|
||||
$sw.Write($json); $sw.Close()
|
||||
|
||||
$response = curl.exe -s -X POST https://ark.cn-beijing.volces.com/api/v3/images/generations `
|
||||
-H "Content-Type: application/json" `
|
||||
-H "Authorization: Bearer ark-119a37ed-f123-42fc-aea6-b38d47d47fc0-f7ddf" `
|
||||
-d "@$tmpFile" | ConvertFrom-Json
|
||||
|
||||
$imageUrl = $response.data[0].url
|
||||
$outputPath = Join-Path (Get-Location) "output-name.png"
|
||||
curl.exe -s -o $outputPath $imageUrl
|
||||
Write-Output $outputPath
|
||||
```
|
||||
|
||||
### 多图融合
|
||||
|
||||
```json
|
||||
{
|
||||
"model": "doubao-seedream-5-0-260128",
|
||||
"prompt": "把图1的人物穿上图2的衣服，站在图3的场景中",
|
||||
"image": ["url1", "url2", "url3"],
|
||||
"size": "2k",
|
||||
"sequential_image_generation": "disabled",
|
||||
"response_format": "url",
|
||||
"stream": false,
|
||||
"watermark": false
|
||||
}
|
||||
```
|
||||
|
||||
### 批量生成（最多15张）
|
||||
|
||||
```json
|
||||
{
|
||||
"model": "doubao-seedream-5-0-260128",
|
||||
"prompt": "一个女孩和她的布偶牛在过山车上，分别呈现早晨、中午、傍晚的场景",
|
||||
"sequential_image_generation": "auto",
|
||||
"sequential_image_generation_options": { "max_images": 3 },
|
||||
"size": "2k",
|
||||
"response_format": "url",
|
||||
"stream": false,
|
||||
"watermark": false
|
||||
}
|
||||
```
|
||||
|
||||
### 豆包参数参考
|
||||
|
||||
| 参数 | 类型 | 必填 | 说明 |
|
||||
|---|---|---|---|
|
||||
| `model` | string | 是 | `doubao-seedream-5-0-260128`（默认）或 `doubao-seededit-3-0-i2i`（精确编辑） |
|
||||
| `prompt` | string | 是 | 文本提示词，最多~300中文字或~600英文词 |
|
||||
| `image` | string[] | 否 | 参考图片URL或Base64（`data:image/png;base64,...`），最多14张 |
|
||||
| `size` | string | 否 | `2k`（默认）、`3k`、`4k` 或 `WIDTHxHEIGHT`（如`2048x1024`），必须小写 |
|
||||
| `response_format` | string | 否 | `url`（下载链接，24h有效）或 `b64_json` |
|
||||
| `sequential_image_generation` | string | 否 | `disabled`（默认，单图）或 `auto`（模型决定批量数） |
|
||||
| `sequential_image_generation_options` | object | 否 | `{ "max_images": N }` N为1-15，仅auto模式 |
|
||||
| `stream` | boolean | 否 | `false`（等待全部）或 `true`（逐张返回） |
|
||||
| `watermark` | boolean | 否 | 添加"AI Generated"水印，默认`false` |
|
||||
| `guidance_scale` | float | 否 | 文本遵循度(CFG)，范围[1,10]，仅seededit-3-0-i2i |
|
||||
| `seed` | int32 | 否 | 可复现种子，仅seededit-3-0-i2i |
|
||||
|
||||
### 豆包尺寸指南
|
||||
|
||||
| 别名 | 近似分辨率 | 适用场景 |
|
||||
|---|---|---|
|
||||
| `2k` | ~2048px | **默认** — 质量与速度平衡 |
|
||||
| `3k` | ~3072px | 高质量，产品图 |
|
||||
| `4k` | ~4096px | 最终生产质量 |
|
||||
| `WIDTHxHEIGHT` | 自定义 | 如`2048x1024`宽幅横幅 |
|
||||
|
||||
像素约束：两个维度必须在[1280, 4096]，最大3:1宽高比。
|
||||
|
||||
### 豆包提示词技巧
|
||||
|
||||
- **描述场景**: 主体、动作、环境、氛围
|
||||
- **指定风格**: "电影大片感"、"水彩画风"、"赛博朋克"、"oc渲染"、"超现实主义"
|
||||
- **质量关键词**: "光线追踪"、"景深"、"极致的光影"、"动态模糊"
|
||||
- **编辑指令**: "把背景换成海滩"、"移除画面中的人物"、"将风格改为水彩画"
|
||||
- **中文提示词原生支持** — 无需翻译为英文
|
||||
|
||||
### Windows注意事项
|
||||
|
||||
| 问题 | 解决方案 |
|
||||
|---|---|
|
||||
| PowerShell 5.1给JSON加UTF-8 BOM | **不要**用`Set-Content`或`[System.Text.Encoding]::UTF8`，用`[System.IO.StreamWriter]::new($path, $false, (New-Object System.Text.UTF8Encoding $false))` |
|
||||
| PowerShell破坏curl中的`"` | **始终**写JSON到临时文件，用`-d "@$tmpFile"` |
|
||||
| curl别名冲突 | 用`curl.exe`而非`curl` |
|
||||
| 续行符 | 用反引号`` ` `` |
|
||||
|
||||
### 豆包错误处理
|
||||
|
||||
- **401**: API Key无效 — 检查Authorization头
|
||||
- **400**: 请求错误 — 检查提示词长度、图片格式、尺寸值
|
||||
- **429**: 限流 — 等待后重试
|
||||
- **500**: 服务器错误 — 稍后重试
|
||||
|
||||
### 精确编辑模型
|
||||
|
||||
需要精细编辑时，`doubao-seededit-3-0-i2i`提供额外控制：
|
||||
|
||||
```json
|
||||
{
|
||||
"model": "doubao-seededit-3-0-i2i",
|
||||
"prompt": "Change the dress color to red",
|
||||
"image": ["data:image/png;base64,..."],
|
||||
"guidance_scale": 5.5,
|
||||
"seed": 42,
|
||||
"size": "adaptive",
|
||||
"response_format": "url",
|
||||
"watermark": false
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 引擎2：阿里云万相2.7
|
||||
|
||||
使用阿里云百炼 **wan2.7-image-pro** 模型，支持文生图、图生图、图片编辑。
|
||||
|
||||
### 前提条件
|
||||
|
||||
环境变量 `DASHSCOPE_API_KEY` 已配置（默认使用内置Key）
|
||||
|
||||
## 基本用法
|
||||
### 基本用法
|
||||
|
||||
```bash
|
||||
python wan_image_edit.py <提示词> <输入图片> [输出路径] [尺寸]
|
||||
@@ -23,7 +199,7 @@ python wan_image_edit.py <提示词> <输入图片> [输出路径] [尺寸]
|
||||
- `输出路径`: 输出文件名（可选，默认 wan_output.png）
|
||||
- `尺寸`: 1K 或 2K（可选，默认 2K）
|
||||
|
||||
## 示例
|
||||
### 示例
|
||||
|
||||
```bash
|
||||
# 白底产品图
|
||||
@@ -32,50 +208,36 @@ python wan_image_edit.py "keep the product, pure white background, professional
|
||||
# 场景图
|
||||
python wan_image_edit.py "place product on modern desk, cozy home office" "product.png" "scene.png"
|
||||
|
||||
# 高性能风格
|
||||
python wan_image_edit.py "cyberpunk gaming setup with RGB lights, benchmark scores" "product.png" "gaming.png" "2K"
|
||||
|
||||
# 文生图（无输入图片）
|
||||
python wan_image_edit.py "futuristic NAS server in data center" "" "t2i.png"
|
||||
|
||||
# 直接在图上添加文字
|
||||
python wan_image_edit.py "keep product, add bold text: 千兆高速传输, professional tech background" "product.png" "with_text.png"
|
||||
```
|
||||
|
||||
## 可用尺寸
|
||||
### 万相2.7可用尺寸
|
||||
|
||||
| 尺寸 | 分辨率 | 适用场景 |
|
||||
|-----|-------|---------|
|
||||
| 1K | 1024x1024 | 快速预览、轮播图 |
|
||||
| 2K | 2048x2048 | 主图、海报（推荐）|
|
||||
|
||||
## 代码调用
|
||||
---
|
||||
|
||||
```python
|
||||
from wan_image_edit import wan_image_edit
|
||||
## 引擎选择建议
|
||||
|
||||
# 基础调用
|
||||
wan_image_edit(
|
||||
prompt="keep the product, white background",
|
||||
image_path="product.png",
|
||||
output_path="output.png",
|
||||
size="2K"
|
||||
)
|
||||
| 场景 | 推荐引擎 | 原因 |
|
||||
|-----|---------|------|
|
||||
| 电商产品主图 | 豆包万相 | 中文提示词支持好，风格丰富 |
|
||||
| 场景图/氛围图 | 豆包万相 | 高质量渲染，支持多种风格 |
|
||||
| 精细图片编辑 | 豆包万相(seededit) | 专用编辑模型，精确控制 |
|
||||
| 多图融合 | 豆包万相 | 原生支持最多14图融合 |
|
||||
| 批量生成 | 豆包万相 | 一次请求最多15张 |
|
||||
| 快速产品抠图/换背景 | 万相2.7 | Python脚本调用便捷 |
|
||||
|
||||
# 批量生成多张
|
||||
styles = [
|
||||
("white bg", "product.png", "white.png"),
|
||||
("cyberpunk", "product.png", "cyber.png"),
|
||||
("data center", "product.png", "datacenter.png"),
|
||||
]
|
||||
for prompt, img, out in styles:
|
||||
wan_image_edit(prompt, img, out)
|
||||
```
|
||||
---
|
||||
|
||||
## 提示词技巧
|
||||
## 输出规范
|
||||
|
||||
- **保持产品**: "keep the product", "retain the original product"
|
||||
- **背景**: "white background", "modern office", "data center"
|
||||
- **风格**: "cyberpunk", "minimalist", "professional"
|
||||
- **氛围**: "dramatic lighting", "warm tones", "neon lights"
|
||||
- **添加文字**: "add bold text: 千兆高速传输"
|
||||
- 保存图片到用户当前工作目录（或子目录）
|
||||
- API返回的URL 24小时内有效 — 立即下载保存到本地
|
||||
- **不要回读图片** — 用markdown显示: ``
|
||||
- 只使用**绝对路径**
|
||||
- 不要在对话中重复路径
|
||||
Reference in New Issue
Block a user