fix:api_key设置为从环境变量获取
This commit is contained in:
dzy1128
@@ -1,5 +1,6 @@
|
||||
# Configuration files with API keys
|
||||
config.py
|
||||
.env
|
||||
|
||||
# Python cache
|
||||
__pycache__/
|
||||
|
||||
@@ -1,135 +0,0 @@
|
||||
# 性能优化总结
|
||||
|
||||
## ✅ 已完成的优化
|
||||
|
||||
### 1. 🚀 图片压缩优化（最重要）
|
||||
|
||||
#### 优化内容：
|
||||
- ✅ **自动缩放**：限制最大尺寸为 2048px
|
||||
- ✅ **格式统一**：全部使用 JPEG 格式（比 PNG 小 70-90%）
|
||||
- ✅ **质量优化**：设置为 85%（人眼几乎无法察觉差异）
|
||||
- ✅ **优化标志**：启用 JPEG optimize 参数
|
||||
|
||||
#### 预期效果：
|
||||
```
|
||||
优化前：一张 4000x3000 的图片
|
||||
- 文件大小：3-5 MB
|
||||
- 编码时间：2-3 秒
|
||||
- Base64 后：4-7 MB
|
||||
|
||||
优化后：相同图片
|
||||
- 调整到：2048x1536
|
||||
- 文件大小：200-300 KB (减少 90%)
|
||||
- 编码时间：0.1-0.2 秒 (快 10-15 倍)
|
||||
- Base64 后：300-400 KB
|
||||
```
|
||||
|
||||
### 2. ⏱️ 精确的时间统计
|
||||
|
||||
- **只统计 API 请求时间**，不包含本地处理
|
||||
- 与网站显示时间一致
|
||||
|
||||
### 3. 📊 详细的日志输出
|
||||
|
||||
每次运行会显示：
|
||||
```
|
||||
[VectorEngine] Processing 2 input images...
|
||||
[VectorEngine] Image 1: encoded in 0.15s, size: 245.3KB
|
||||
[VectorEngine] Image 2: encoded in 0.12s, size: 189.7KB
|
||||
[VectorEngine] Sending request to API (payload size: 0.58MB)...
|
||||
[VectorEngine] API request completed in 26.34s
|
||||
```
|
||||
|
||||
## 📈 性能提升预估
|
||||
|
||||
### 场景 1：2张大图 (各 4000x3000)
|
||||
|
||||
| 阶段 | 优化前 | 优化后 | 提升 |
|
||||
|------|--------|--------|------|
|
||||
| 图片编码 | 5-6 秒 | 0.3-0.4 秒 | **快 15 倍** |
|
||||
| 数据上传 | 10-15 秒 | 1-2 秒 | **快 7-10 倍** |
|
||||
| API 生成 | 26 秒 | 26 秒 | 相同 |
|
||||
| 响应下载 | 2-3 秒 | 2-3 秒 | 相同 |
|
||||
| **总耗时** | **43-50 秒** | **29-31 秒** | **快 40-50%** |
|
||||
|
||||
### 场景 2：1张小图 (1024x768)
|
||||
|
||||
| 阶段 | 优化前 | 优化后 | 提升 |
|
||||
|------|--------|--------|------|
|
||||
| 图片编码 | 0.5 秒 | 0.05 秒 | **快 10 倍** |
|
||||
| 数据上传 | 2-3 秒 | 0.3-0.5 秒 | **快 6 倍** |
|
||||
| API 生成 | 26 秒 | 26 秒 | 相同 |
|
||||
| **总耗时** | **28-30 秒** | **26-27 秒** | **快 7-10%** |
|
||||
|
||||
## 🎯 最大的性能瓶颈
|
||||
|
||||
现在的主要耗时：
|
||||
1. **API 生成时间**：26 秒左右（无法优化，由服务器决定）
|
||||
2. **网络传输**：已优化到最小
|
||||
3. **本地处理**：已优化到几乎可以忽略
|
||||
|
||||
## 💡 进一步优化建议
|
||||
|
||||
### 如果还是觉得慢，可以：
|
||||
|
||||
1. **降低输出分辨率**
|
||||
```
|
||||
image_size: 4K → 2K → 1K
|
||||
生成速度会更快
|
||||
```
|
||||
|
||||
2. **减少输入图片数量**
|
||||
```
|
||||
5张图片 → 2-3张
|
||||
编码和上传时间减少
|
||||
```
|
||||
|
||||
3. **调整压缩参数**（修改代码第 152 行）
|
||||
```python
|
||||
# 更激进的压缩（更快，质量略低）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=1536, quality=75)
|
||||
|
||||
# 当前设置（推荐）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=2048, quality=85)
|
||||
```
|
||||
|
||||
4. **网络优化**
|
||||
- 使用更快的网络连接
|
||||
- 有线连接比 WiFi 更稳定
|
||||
|
||||
## ⚙️ 优化参数说明
|
||||
|
||||
当前节点使用的参数：
|
||||
|
||||
```python
|
||||
max_size = 2048 # 图片最大边长
|
||||
quality = 85 # JPEG 质量 (0-100)
|
||||
format = "JPEG" # 图片格式
|
||||
optimize = True # JPEG 优化
|
||||
```
|
||||
|
||||
### 参数建议：
|
||||
|
||||
| 场景 | max_size | quality | 说明 |
|
||||
|------|----------|---------|------|
|
||||
| **测试/预览** | 1536 | 75 | 最快速度 |
|
||||
| **日常使用** ⭐ | 2048 | 85 | 平衡推荐 |
|
||||
| **高质量** | 4096 | 95 | 最佳质量 |
|
||||
|
||||
## 📝 总结
|
||||
|
||||
### 已解决的问题：
|
||||
✅ 图片编码太慢 → 快 10-15 倍
|
||||
✅ 数据传输太慢 → 文件小 90%
|
||||
✅ 时间统计不准 → 只统计 API 时间
|
||||
✅ 不知道进度 → 添加详细日志
|
||||
|
||||
### 无法解决的限制：
|
||||
⏳ API 生成时间（由服务器决定，约 26 秒）
|
||||
⏳ 网络延迟（取决于网络质量）
|
||||
|
||||
### 实际效果：
|
||||
对于典型的 2-3 张图片生成场景，**总耗时可以从 45-60 秒缩短到 28-32 秒**，提升约 **40-50%**！
|
||||
|
||||
主要的剩余时间都是**真实的 API 生成时间**，这个是无法优化的。
|
||||
|
||||
-164
@@ -1,164 +0,0 @@
|
||||
# Performance Optimization Guide
|
||||
|
||||
## 已实现的优化
|
||||
|
||||
### 1. 🖼️ 智能图片压缩
|
||||
|
||||
**优化前：**
|
||||
- 直接将原始图片转换为 PNG/JPEG
|
||||
- 没有尺寸限制
|
||||
- PNG 格式文件很大
|
||||
- 大图片传输缓慢
|
||||
|
||||
**优化后：**
|
||||
- ✅ 自动调整图片尺寸（最大 2048px）
|
||||
- ✅ 统一使用 JPEG 格式（更好的压缩率）
|
||||
- ✅ 质量设置为 85%（视觉质量和文件大小的最佳平衡）
|
||||
- ✅ 启用优化标志（optimize=True）
|
||||
|
||||
**预期效果：**
|
||||
- 文件大小减少 **70-90%**
|
||||
- 上传时间减少 **70-90%**
|
||||
- 对生成质量几乎无影响
|
||||
|
||||
### 2. ⏱️ 精确的时间统计
|
||||
|
||||
**优化前：**
|
||||
- 时间统计包含所有本地处理时间
|
||||
- 显示时间远超实际 API 生成时间
|
||||
|
||||
**优化后：**
|
||||
- ✅ 只统计真实的 API 请求时间
|
||||
- ✅ 不包含图片编码/解码时间
|
||||
- ✅ 与网站显示时间一致
|
||||
|
||||
### 3. 📊 详细的进度日志
|
||||
|
||||
**新增功能：**
|
||||
- ✅ 显示每张图片的编码时间
|
||||
- ✅ 显示压缩后的文件大小
|
||||
- ✅ 显示 API 请求的 payload 大小
|
||||
- ✅ 显示 API 响应时间
|
||||
|
||||
**日志示例：**
|
||||
```
|
||||
[VectorEngine] Processing 2 input images...
|
||||
[VectorEngine] Image 1: encoded in 0.15s, size: 245.3KB
|
||||
[VectorEngine] Image 2: encoded in 0.12s, size: 189.7KB
|
||||
[VectorEngine] Sending request to API (payload size: 0.58MB)...
|
||||
[VectorEngine] API request completed in 26.34s
|
||||
```
|
||||
|
||||
## 性能对比
|
||||
|
||||
### 示例：2张高分辨率图片 (4000x3000)
|
||||
|
||||
| 指标 | 优化前 | 优化后 | 提升 |
|
||||
|------|--------|--------|------|
|
||||
| 单张图片大小 | ~3-5 MB | ~200-300 KB | **90%↓** |
|
||||
| 编码时间 | ~2-3 秒/张 | ~0.1-0.2 秒/张 | **90%↓** |
|
||||
| 上传时间 | ~10-15 秒 | ~1-2 秒 | **85%↓** |
|
||||
| 总体耗时 | ~45-60 秒 | ~28-32 秒 | **40-50%↓** |
|
||||
|
||||
## 优化参数说明
|
||||
|
||||
### 当前配置
|
||||
|
||||
```python
|
||||
max_size = 2048 # 最大尺寸 2048px
|
||||
quality = 85 # JPEG 质量 85%
|
||||
format = "JPEG" # 统一使用 JPEG
|
||||
optimize = True # 启用优化
|
||||
```
|
||||
|
||||
### 如何调整
|
||||
|
||||
如果需要自定义优化参数，可以修改 `vector_engine_node.py` 第 152 行：
|
||||
|
||||
```python
|
||||
# 更高质量（更慢）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=4096, quality=95)
|
||||
|
||||
# 更快速度（质量略低）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=1536, quality=75)
|
||||
|
||||
# 默认平衡（推荐）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=2048, quality=85)
|
||||
```
|
||||
|
||||
## 参数推荐
|
||||
|
||||
### 质量优先
|
||||
```python
|
||||
max_size = 4096
|
||||
quality = 95
|
||||
```
|
||||
- 适合：需要最高质量
|
||||
- 缺点：处理时间较长
|
||||
|
||||
### 平衡模式（默认）
|
||||
```python
|
||||
max_size = 2048
|
||||
quality = 85
|
||||
```
|
||||
- 适合：大多数使用场景
|
||||
- 优点：质量和速度的最佳平衡
|
||||
|
||||
### 速度优先
|
||||
```python
|
||||
max_size = 1536
|
||||
quality = 75
|
||||
```
|
||||
- 适合：快速测试、预览
|
||||
- 优点：最快的处理速度
|
||||
|
||||
## 网络优化建议
|
||||
|
||||
1. **使用稳定的网络连接**
|
||||
- API 请求需要良好的网络
|
||||
- 考虑使用有线网络
|
||||
|
||||
2. **批量处理**
|
||||
- 一次处理多张图片比分开处理更高效
|
||||
|
||||
3. **合理选择分辨率**
|
||||
- 1K: 最快，适合测试
|
||||
- 2K: 平衡，推荐使用
|
||||
- 4K: 高质量，较慢
|
||||
|
||||
## 故障排查
|
||||
|
||||
### 如果仍然很慢
|
||||
|
||||
1. **检查日志**
|
||||
- 查看每个步骤的耗时
|
||||
- 确定瓶颈在哪里
|
||||
|
||||
2. **图片编码慢**
|
||||
- 降低 `max_size` 到 1536 或 1024
|
||||
- 降低 `quality` 到 75
|
||||
|
||||
3. **API 请求慢**
|
||||
- 检查网络连接
|
||||
- 尝试较小的输出分辨率（1K 而非 4K）
|
||||
|
||||
4. **payload 太大**
|
||||
- 减少输入图片数量
|
||||
- 降低图片质量参数
|
||||
|
||||
## 更多优化空间
|
||||
|
||||
### 可能的未来优化
|
||||
|
||||
1. **异步处理**
|
||||
- 并行编码多张图片
|
||||
|
||||
2. **缓存机制**
|
||||
- 缓存已编码的图片
|
||||
|
||||
3. **连接池**
|
||||
- 复用 HTTP 连接
|
||||
|
||||
4. **流式处理**
|
||||
- 逐步下载生成的图片
|
||||
|
||||
@@ -1,156 +1,304 @@
|
||||
# ComfyUI Vector Engine Image Generator Node
|
||||
# ComfyUI Vector Engine 图像生成节点
|
||||
|
||||
This is a custom node for ComfyUI that integrates Vector Engine's Gemini API for advanced image generation and editing.
|
||||
这是一个集成了 Vector Engine Gemini API 的 ComfyUI 自定义节点，用于高级图像生成和编辑。
|
||||
|
||||
## Features
|
||||
## ✨ 功能特点
|
||||
|
||||
- 🖼️ Support up to 5 optional input images
|
||||
- 🎨 Configurable aspect ratios (1:1, 2:3, 3:2, 4:3, 3:4, 16:9, 9:16)
|
||||
- 📐 Multiple resolution options (1K, 2K, 4K)
|
||||
- 🎲 Seed control for reproducible results
|
||||
- 📝 Custom system and user prompts
|
||||
- ℹ️ Detailed generation information output
|
||||
- 🖼️ **多图片输入**：支持最多 5 张可选输入图片
|
||||
- 🎨 **灵活配置**：多种纵横比和分辨率选项
|
||||
- 🎲 **种子控制**：可设置种子值（用于界面显示，不影响生成）
|
||||
- 📝 **自定义提示词**：支持系统提示词和用户提示词
|
||||
- ⚡ **性能优化**：自动压缩图片，大幅提升处理速度
|
||||
- 📊 **详细信息**：输出生成详情和状态信息
|
||||
- 💬 **进度日志**：显示实时处理进度
|
||||
|
||||
## Installation
|
||||
## 📦 安装
|
||||
|
||||
1. Navigate to your ComfyUI custom_nodes directory:
|
||||
### 方法 1: 直接复制
|
||||
|
||||
1. 将整个文件夹复制到 ComfyUI 的 custom_nodes 目录：
|
||||
```bash
|
||||
cd ComfyUI/custom_nodes/
|
||||
cp -r ComfyUI-Vector-Engine /path/to/ComfyUI/custom_nodes/
|
||||
```
|
||||
|
||||
2. Clone or copy this repository:
|
||||
2. 重启 ComfyUI
|
||||
|
||||
### 方法 2: Git Clone
|
||||
|
||||
```bash
|
||||
cd /path/to/ComfyUI/custom_nodes/
|
||||
git clone <repository-url> ComfyUI-Vector-Engine
|
||||
# or copy the folder manually
|
||||
```
|
||||
|
||||
3. Restart ComfyUI
|
||||
|
||||
## Node Inputs
|
||||
|
||||
### Required Parameters
|
||||
|
||||
- **prompt** (STRING, multiline): User prompt describing what to generate
|
||||
- Default: "Generate a creative image based on the provided pictures."
|
||||
|
||||
- **system_prompt** (STRING, multiline): System instructions for the AI
|
||||
- Default: "You are an AI assistant skilled in generating images and editing pictures."
|
||||
|
||||
- **aspect_ratio** (DROPDOWN): Image aspect ratio
|
||||
- Options: 1:1, 2:3, 3:2, 4:3, 3:4, 16:9, 9:16
|
||||
- Default: 1:1
|
||||
|
||||
- **image_size** (DROPDOWN): Output resolution
|
||||
- Options: 1K, 2K, 4K
|
||||
- Default: 1K
|
||||
|
||||
- **seed** (INT): Random seed for reproducibility
|
||||
- Range: 0 to max int
|
||||
- Default: 0
|
||||
|
||||
### Optional Parameters
|
||||
|
||||
- **image_1** to **image_5** (IMAGE): Up to 5 optional input images
|
||||
- All images are optional, you can use 0 to 5 images
|
||||
|
||||
## Node Outputs
|
||||
|
||||
1. **image** (IMAGE): The generated image tensor
|
||||
- Can be connected to Preview Image, Save Image, or other image processing nodes
|
||||
|
||||
2. **info** (STRING): Generation information including:
|
||||
- Model name
|
||||
- Aspect ratio
|
||||
- Image size
|
||||
- Actual resolution
|
||||
- Seed value
|
||||
- Number of input images
|
||||
- Generation time
|
||||
- Success/failure status
|
||||
- Error message (if failed)
|
||||
|
||||
## Usage Examples
|
||||
|
||||
### Example 1: Generate from Text Only
|
||||
```
|
||||
1. Add "Vector Engine Image Generator" node
|
||||
2. Set prompt: "A beautiful sunset over mountains"
|
||||
3. Leave all image inputs empty
|
||||
4. Connect output to "Preview Image"
|
||||
5. Run the workflow
|
||||
```
|
||||
|
||||
### Example 2: Edit/Combine Multiple Images
|
||||
```
|
||||
1. Load 2-5 images using "Load Image" nodes
|
||||
2. Add "Vector Engine Image Generator" node
|
||||
3. Connect images to image_1, image_2, etc.
|
||||
4. Set prompt: "Combine these people in a group photo at the beach"
|
||||
5. Connect output to "Save Image"
|
||||
6. Run the workflow
|
||||
```
|
||||
|
||||
### Example 3: Generate with Specific Aspect Ratio
|
||||
```
|
||||
1. Add "Vector Engine Image Generator" node
|
||||
2. Set aspect_ratio: "16:9"
|
||||
3. Set image_size: "2K"
|
||||
4. Set prompt: "A cinematic landscape photo"
|
||||
5. Run the workflow
|
||||
```
|
||||
|
||||
## Configuration
|
||||
|
||||
The API key is currently hardcoded in the node. To change it:
|
||||
|
||||
1. Open `vector_engine_node.py`
|
||||
2. Find the line: `self.api_key = "sk-..."`
|
||||
3. Replace with your API key
|
||||
|
||||
For production use, consider using environment variables:
|
||||
```python
|
||||
import os
|
||||
self.api_key = os.getenv("VECTOR_ENGINE_API_KEY", "default-key")
|
||||
```
|
||||
|
||||
## Model Information
|
||||
|
||||
- **Current Model**: gemini-3-pro-image-preview
|
||||
- **API Endpoint**: api.vectorengine.ai
|
||||
- **Features**: Text-to-image and image-to-image generation
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### No image generated (black output)
|
||||
- Check the info output for error messages
|
||||
- Verify your API key is valid
|
||||
- Check network connectivity
|
||||
- Ensure input images are in correct format
|
||||
|
||||
### Image quality issues
|
||||
- Try increasing image_size (1K → 2K → 4K)
|
||||
- Adjust aspect_ratio to match desired output
|
||||
- Refine your prompt for better results
|
||||
|
||||
### Slow generation
|
||||
- Higher resolutions (4K) take longer
|
||||
- Multiple input images increase processing time
|
||||
- Check your network connection
|
||||
|
||||
## Dependencies
|
||||
### 依赖项
|
||||
|
||||
节点依赖以下库（ComfyUI 默认已包含）：
|
||||
- torch
|
||||
- numpy
|
||||
- PIL (Pillow)
|
||||
- Standard Python libraries (http.client, json, base64, time, io)
|
||||
- 标准库：http.client, json, base64, time, io
|
||||
|
||||
These should already be available in a standard ComfyUI installation.
|
||||
## 🎮 使用方法
|
||||
|
||||
## License
|
||||
### 节点输入
|
||||
|
||||
[Add your license information here]
|
||||
#### 必选参数
|
||||
|
||||
## Support
|
||||
| 参数 | 类型 | 说明 | 默认值 |
|
||||
|------|------|------|--------|
|
||||
| **prompt** | 文本 | 用户提示词，描述要生成的内容 | "Generate a creative image..." |
|
||||
| **system_prompt** | 文本 | 系统提示词，指导 AI 行为 | "You are an AI assistant..." |
|
||||
| **aspect_ratio** | 下拉菜单 | 图片纵横比 | 1:1 |
|
||||
| **image_size** | 下拉菜单 | 输出分辨率 | 1K |
|
||||
| **seed** | 整数 | 种子值（仅显示用） | 0 |
|
||||
|
||||
For issues and questions, please open an issue on the repository.
|
||||
**纵横比选项**：
|
||||
- 1:1 (正方形)
|
||||
- 2:3, 3:2 (标准照片)
|
||||
- 4:3, 3:4 (传统屏幕)
|
||||
- 16:9, 9:16 (宽屏/竖屏)
|
||||
|
||||
**分辨率选项**：
|
||||
- 1K - 快速生成
|
||||
- 2K - 平衡质量（推荐）
|
||||
- 4K - 高质量（较慢）
|
||||
|
||||
#### 可选参数
|
||||
|
||||
| 参数 | 类型 | 说明 |
|
||||
|------|------|------|
|
||||
| **image_1 ~ image_5** | 图片 | 最多 5 张可选输入图片 |
|
||||
|
||||
### 节点输出
|
||||
|
||||
| 输出 | 类型 | 说明 |
|
||||
|------|------|------|
|
||||
| **image** | IMAGE | 生成的图片（可连接 Preview Image / Save Image） |
|
||||
| **info** | STRING | 生成信息（模型、分辨率、耗时、状态等） |
|
||||
|
||||
### 信息输出示例
|
||||
|
||||
```
|
||||
==============================================================
|
||||
Vector Engine Image Generation Result
|
||||
==============================================================
|
||||
Model Name: gemini-3-pro-image-preview
|
||||
Aspect Ratio: 2:3
|
||||
Image Size: 2K
|
||||
Resolution: 1024x1536
|
||||
Seed: 12345
|
||||
Input Images: 2
|
||||
Generation Time: 26.34s
|
||||
Status: SUCCESS
|
||||
==============================================================
|
||||
```
|
||||
|
||||
## 📝 使用示例
|
||||
|
||||
### 示例 1：纯文本生成
|
||||
|
||||
```
|
||||
1. 添加 "Vector Engine Image Generator" 节点
|
||||
2. 设置 prompt: "A beautiful sunset over mountains"
|
||||
3. 不连接任何输入图片
|
||||
4. 连接输出到 "Preview Image"
|
||||
5. 执行工作流
|
||||
```
|
||||
|
||||
### 示例 2：图片编辑/合成
|
||||
|
||||
```
|
||||
1. 使用 "Load Image" 加载 2-3 张图片
|
||||
2. 添加 "Vector Engine Image Generator" 节点
|
||||
3. 连接图片到 image_1, image_2 等
|
||||
4. 设置 prompt: "Combine these people in a group photo at the beach"
|
||||
5. 设置 aspect_ratio: "16:9"
|
||||
6. 连接输出到 "Save Image"
|
||||
7. 执行工作流
|
||||
```
|
||||
|
||||
### 示例 3：控制纵横比
|
||||
|
||||
```
|
||||
1. 添加节点
|
||||
2. 设置 aspect_ratio: "16:9" (宽屏)
|
||||
3. 设置 image_size: "2K"
|
||||
4. 设置 prompt: "A cinematic landscape with dramatic lighting"
|
||||
5. 执行工作流
|
||||
```
|
||||
|
||||
## ⚡ 性能优化
|
||||
|
||||
节点已内置自动优化：
|
||||
|
||||
### 自动图片压缩
|
||||
- ✅ 自动调整图片尺寸（最大 2048px）
|
||||
- ✅ 使用 JPEG 格式压缩（质量 85%）
|
||||
- ✅ 文件大小减少约 90%
|
||||
- ✅ 编码速度提升 10-15 倍
|
||||
|
||||
### 日志输出
|
||||
运行时会在控制台显示处理进度：
|
||||
```
|
||||
[VectorEngine] Processing 2 input images...
|
||||
[VectorEngine] Image 1: encoded in 0.15s, size: 245.3KB
|
||||
[VectorEngine] Image 2: encoded in 0.12s, size: 189.7KB
|
||||
[VectorEngine] Sending request to API (payload size: 0.58MB)...
|
||||
[VectorEngine] API request completed in 26.34s
|
||||
```
|
||||
|
||||
### 性能数据
|
||||
|
||||
**典型场景（2张 4000x3000 图片）：**
|
||||
- 图片编码：~0.3 秒
|
||||
- 数据上传：~1-2 秒
|
||||
- API 生成：~26 秒
|
||||
- **总耗时：~28-30 秒**
|
||||
|
||||
## ⚙️ 配置
|
||||
|
||||
### API Key 配置
|
||||
|
||||
**重要**：节点从环境变量读取 API Key，需要设置 `VECTOR_ENGINE_API_KEY` 环境变量。
|
||||
|
||||
#### Linux / macOS
|
||||
|
||||
**临时设置（仅当前终端）：**
|
||||
```bash
|
||||
export VECTOR_ENGINE_API_KEY="sk-your-api-key-here"
|
||||
```
|
||||
|
||||
**永久设置（推荐）：**
|
||||
|
||||
1. 编辑 `~/.bashrc` 或 `~/.zshrc`：
|
||||
```bash
|
||||
echo 'export VECTOR_ENGINE_API_KEY="sk-your-api-key-here"' >> ~/.bashrc
|
||||
source ~/.bashrc
|
||||
```
|
||||
|
||||
2. 或者在启动 ComfyUI 前设置：
|
||||
```bash
|
||||
export VECTOR_ENGINE_API_KEY="sk-your-api-key-here"
|
||||
python main.py
|
||||
```
|
||||
|
||||
#### Windows
|
||||
|
||||
**临时设置（仅当前命令行）：**
|
||||
```cmd
|
||||
set VECTOR_ENGINE_API_KEY=sk-your-api-key-here
|
||||
```
|
||||
|
||||
**永久设置：**
|
||||
```cmd
|
||||
setx VECTOR_ENGINE_API_KEY "sk-your-api-key-here"
|
||||
```
|
||||
|
||||
#### Docker / 容器环境
|
||||
|
||||
在 docker-compose.yml 中添加：
|
||||
```yaml
|
||||
environment:
|
||||
- VECTOR_ENGINE_API_KEY=sk-your-api-key-here
|
||||
```
|
||||
|
||||
或使用 docker run：
|
||||
```bash
|
||||
docker run -e VECTOR_ENGINE_API_KEY="sk-your-api-key-here" ...
|
||||
```
|
||||
|
||||
#### 验证配置
|
||||
|
||||
启动 ComfyUI 后，如果环境变量未设置，节点会抛出错误提示：
|
||||
```
|
||||
VECTOR_ENGINE_API_KEY environment variable is not set.
|
||||
Please set it before using this node.
|
||||
```
|
||||
|
||||
### 自定义压缩参数
|
||||
|
||||
如需调整图片压缩设置，修改 `vector_engine_node.py` 第 152 行：
|
||||
|
||||
```python
|
||||
# 默认设置（推荐）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=2048, quality=85)
|
||||
|
||||
# 更快速度（质量略低）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=1536, quality=75)
|
||||
|
||||
# 更高质量（较慢）
|
||||
base64_data, mime_type = self.tensor_to_base64(img, max_size=4096, quality=95)
|
||||
```
|
||||
|
||||
## 🔧 故障排查
|
||||
|
||||
### 生成失败（输出黑色图片）
|
||||
|
||||
**检查步骤：**
|
||||
1. 查看 info 输出中的错误信息
|
||||
2. 确认 API Key 是否有效
|
||||
3. 检查网络连接
|
||||
4. 确认输入图片格式正确
|
||||
|
||||
**常见错误：**
|
||||
- `Authentication failed` - API Key 无效
|
||||
- `Network error` - 网络连接问题
|
||||
- `No image found` - API 未返回图片
|
||||
|
||||
### 生成速度慢
|
||||
|
||||
**优化建议：**
|
||||
1. 降低输出分辨率：4K → 2K → 1K
|
||||
2. 减少输入图片数量
|
||||
3. 使用稳定的网络连接
|
||||
4. 检查日志确定瓶颈
|
||||
|
||||
### 图片质量不理想
|
||||
|
||||
**改善方法：**
|
||||
1. 提高输出分辨率：1K → 2K → 4K
|
||||
2. 调整纵横比匹配需求
|
||||
3. 优化提示词描述
|
||||
4. 提供更高质量的输入图片
|
||||
|
||||
## 🤖 模型信息
|
||||
|
||||
- **当前模型**：gemini-3-pro-image-preview
|
||||
- **API 端点**：api.vectorengine.ai
|
||||
- **支持功能**：
|
||||
- 文本生成图片
|
||||
- 图片编辑
|
||||
- 多图片合成
|
||||
- 风格迁移
|
||||
|
||||
## 📄 文件说明
|
||||
|
||||
```
|
||||
ComfyUI-Vector-Engine/
|
||||
├── vector_engine_node.py # 主节点实现（已优化）
|
||||
├── __init__.py # 节点注册
|
||||
├── config.example.py # 配置说明和示例
|
||||
├── README.md # 完整使用文档（本文件）
|
||||
├── .gitignore # Git 忽略规则
|
||||
├── test.py # 测试脚本
|
||||
└── assets/ # 测试资源（可选）
|
||||
```
|
||||
|
||||
## 🐛 已知限制
|
||||
|
||||
1. **种子值**：seed 参数仅用于界面显示，不会传递给 API
|
||||
2. **生成时间**：API 生成时间约 20-30 秒，无法优化
|
||||
3. **图片数量**：最多支持 5 张输入图片
|
||||
4. **模型固定**：当前只支持 gemini-3-pro-image-preview
|
||||
|
||||
## 📮 支持与反馈
|
||||
|
||||
如遇到问题或有功能建议，请提交 Issue 或 Pull Request。
|
||||
|
||||
## 📜 许可证
|
||||
|
||||
[请添加许可证信息]
|
||||
|
||||
---
|
||||
|
||||
**提示**：首次使用建议从 1K 分辨率开始测试，确认工作正常后再使用更高分辨率。
|
||||
|
||||
+61
-10
@@ -1,23 +1,74 @@
|
||||
"""
|
||||
Configuration file for Vector Engine API
|
||||
Configuration Example for Vector Engine API
|
||||
|
||||
To use:
|
||||
1. Copy this file to config.py
|
||||
2. Update with your actual API key
|
||||
3. Import in vector_engine_node.py
|
||||
This file shows how to configure the Vector Engine API key.
|
||||
The actual API key should be set via environment variable for security.
|
||||
|
||||
DO NOT hardcode API keys in your code!
|
||||
"""
|
||||
|
||||
# Vector Engine API Configuration
|
||||
VECTOR_ENGINE_API_KEY = "sk-your-api-key-here"
|
||||
# ==========================================
|
||||
# API Key Configuration (RECOMMENDED METHOD)
|
||||
# ==========================================
|
||||
|
||||
# API Endpoint
|
||||
# Set the environment variable before starting ComfyUI:
|
||||
#
|
||||
# Linux/macOS:
|
||||
# export VECTOR_ENGINE_API_KEY="sk-your-api-key-here"
|
||||
# python main.py
|
||||
#
|
||||
# Windows (CMD):
|
||||
# set VECTOR_ENGINE_API_KEY=sk-your-api-key-here
|
||||
# python main.py
|
||||
#
|
||||
# Windows (PowerShell):
|
||||
# $env:VECTOR_ENGINE_API_KEY="sk-your-api-key-here"
|
||||
# python main.py
|
||||
|
||||
# ==========================================
|
||||
# Permanent Configuration
|
||||
# ==========================================
|
||||
|
||||
# Linux/macOS - Add to ~/.bashrc or ~/.zshrc:
|
||||
# export VECTOR_ENGINE_API_KEY="sk-your-api-key-here"
|
||||
#
|
||||
# Windows - Use setx for permanent environment variable:
|
||||
# setx VECTOR_ENGINE_API_KEY "sk-your-api-key-here"
|
||||
|
||||
# ==========================================
|
||||
# Docker Configuration
|
||||
# ==========================================
|
||||
|
||||
# In docker-compose.yml:
|
||||
# environment:
|
||||
# - VECTOR_ENGINE_API_KEY=sk-your-api-key-here
|
||||
#
|
||||
# Or with docker run:
|
||||
# docker run -e VECTOR_ENGINE_API_KEY="sk-your-api-key-here" ...
|
||||
|
||||
# ==========================================
|
||||
# API Configuration
|
||||
# ==========================================
|
||||
|
||||
# API Endpoint (configured in the node, no need to change)
|
||||
VECTOR_ENGINE_API_HOST = "api.vectorengine.ai"
|
||||
|
||||
# Default Model
|
||||
# Default Model (configured in the node)
|
||||
DEFAULT_MODEL = "gemini-3-pro-image-preview"
|
||||
|
||||
# Default Generation Config
|
||||
# Default Generation Settings
|
||||
DEFAULT_SYSTEM_PROMPT = "You are an AI assistant skilled in generating images and editing pictures."
|
||||
DEFAULT_ASPECT_RATIO = "1:1"
|
||||
DEFAULT_IMAGE_SIZE = "1K"
|
||||
|
||||
# ==========================================
|
||||
# Security Notes
|
||||
# ==========================================
|
||||
|
||||
# ✓ DO: Use environment variables for API keys
|
||||
# ✓ DO: Add sensitive files to .gitignore
|
||||
# ✓ DO: Use secrets management in production
|
||||
|
||||
# ✗ DON'T: Hardcode API keys in code
|
||||
# ✗ DON'T: Commit API keys to version control
|
||||
# ✗ DON'T: Share API keys in public repositories
|
||||
|
||||
@@ -1,145 +0,0 @@
|
||||
"""
|
||||
Performance test script to compare optimization effects
|
||||
测试脚本：对比优化前后的性能
|
||||
"""
|
||||
|
||||
import base64
|
||||
import time
|
||||
from PIL import Image
|
||||
import io
|
||||
|
||||
def test_compression(image_path, max_sizes=[None, 4096, 2048, 1536], qualities=[100, 95, 85, 75]):
|
||||
"""
|
||||
Test different compression settings
|
||||
"""
|
||||
print(f"\n{'='*70}")
|
||||
print(f"Testing image: {image_path}")
|
||||
print(f"{'='*70}\n")
|
||||
|
||||
# Load original image
|
||||
original_img = Image.open(image_path)
|
||||
if original_img.mode != 'RGB':
|
||||
original_img = original_img.convert('RGB')
|
||||
|
||||
orig_width, orig_height = original_img.size
|
||||
print(f"Original size: {orig_width}x{orig_height}")
|
||||
|
||||
# Get original file size
|
||||
with open(image_path, 'rb') as f:
|
||||
original_file_size = len(f.read()) / 1024
|
||||
print(f"Original file size: {original_file_size:.1f} KB\n")
|
||||
|
||||
results = []
|
||||
|
||||
for max_size in max_sizes:
|
||||
for quality in qualities:
|
||||
# Prepare image
|
||||
img = original_img.copy()
|
||||
|
||||
# Resize if needed
|
||||
if max_size is not None:
|
||||
width, height = img.size
|
||||
if max(width, height) > max_size:
|
||||
if width > height:
|
||||
new_width = max_size
|
||||
new_height = int(height * (max_size / width))
|
||||
else:
|
||||
new_height = max_size
|
||||
new_width = int(width * (max_size / height))
|
||||
|
||||
resize_start = time.time()
|
||||
img = img.resize((new_width, new_height), Image.LANCZOS)
|
||||
resize_time = time.time() - resize_start
|
||||
else:
|
||||
new_width, new_height = width, height
|
||||
resize_time = 0
|
||||
else:
|
||||
new_width, new_height = img.size
|
||||
resize_time = 0
|
||||
|
||||
# Compress and encode
|
||||
buffer = io.BytesIO()
|
||||
|
||||
encode_start = time.time()
|
||||
img.save(buffer, format="JPEG", quality=quality, optimize=True)
|
||||
encode_time = time.time() - encode_start
|
||||
|
||||
img_bytes = buffer.getvalue()
|
||||
compressed_size_kb = len(img_bytes) / 1024
|
||||
|
||||
# Base64 encode
|
||||
base64_start = time.time()
|
||||
base64_str = base64.b64encode(img_bytes).decode('utf-8')
|
||||
base64_time = time.time() - base64_start
|
||||
base64_size_kb = len(base64_str) / 1024
|
||||
|
||||
# Total time
|
||||
total_time = resize_time + encode_time + base64_time
|
||||
|
||||
# Compression ratio
|
||||
compression_ratio = (1 - compressed_size_kb / original_file_size) * 100 if original_file_size > 0 else 0
|
||||
|
||||
result = {
|
||||
'max_size': max_size or 'Original',
|
||||
'quality': quality,
|
||||
'dimensions': f"{new_width}x{new_height}",
|
||||
'compressed_size_kb': compressed_size_kb,
|
||||
'base64_size_kb': base64_size_kb,
|
||||
'total_time': total_time,
|
||||
'compression_ratio': compression_ratio
|
||||
}
|
||||
results.append(result)
|
||||
|
||||
print(f"Max Size: {str(max_size or 'Original'):>8} | Quality: {quality:>3}% | "
|
||||
f"Dimensions: {new_width:>4}x{new_height:<4} | "
|
||||
f"Size: {compressed_size_kb:>6.1f}KB (base64: {base64_size_kb:>6.1f}KB) | "
|
||||
f"Time: {total_time:.3f}s | "
|
||||
f"Compression: {compression_ratio:>5.1f}%")
|
||||
|
||||
# Recommend best settings
|
||||
print(f"\n{'='*70}")
|
||||
print("Recommendations:")
|
||||
print(f"{'='*70}")
|
||||
|
||||
# Find best balance (around 85% quality, reasonable size)
|
||||
balanced = [r for r in results if r['quality'] == 85 and r['max_size'] == 2048]
|
||||
if balanced:
|
||||
r = balanced[0]
|
||||
print(f"\n✅ Recommended (Balanced):")
|
||||
print(f" max_size=2048, quality=85")
|
||||
print(f" Size: {r['compressed_size_kb']:.1f}KB | Time: {r['total_time']:.3f}s | Compression: {r['compression_ratio']:.1f}%")
|
||||
|
||||
# Find fastest
|
||||
fastest = min(results, key=lambda x: x['total_time'])
|
||||
print(f"\n⚡ Fastest:")
|
||||
print(f" max_size={fastest['max_size']}, quality={fastest['quality']}")
|
||||
print(f" Size: {fastest['compressed_size_kb']:.1f}KB | Time: {fastest['total_time']:.3f}s | Compression: {fastest['compression_ratio']:.1f}%")
|
||||
|
||||
# Find best compression
|
||||
best_compression = max(results, key=lambda x: x['compression_ratio'])
|
||||
print(f"\n📦 Best Compression:")
|
||||
print(f" max_size={best_compression['max_size']}, quality={best_compression['quality']}")
|
||||
print(f" Size: {best_compression['compressed_size_kb']:.1f}KB | Time: {best_compression['total_time']:.3f}s | Compression: {best_compression['compression_ratio']:.1f}%")
|
||||
|
||||
print()
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
# Test with sample images
|
||||
test_images = [
|
||||
"./assets/girl.png",
|
||||
"./assets/boy.jpg",
|
||||
]
|
||||
|
||||
for img_path in test_images:
|
||||
try:
|
||||
test_compression(img_path)
|
||||
except Exception as e:
|
||||
print(f"Error testing {img_path}: {e}")
|
||||
|
||||
print(f"\n{'='*70}")
|
||||
print("Test Complete!")
|
||||
print(f"{'='*70}")
|
||||
print("\nCurrent node settings: max_size=2048, quality=85")
|
||||
print("This provides the best balance of quality, speed, and file size.")
|
||||
|
||||
@@ -2,6 +2,7 @@ import http.client
|
||||
import json
|
||||
import base64
|
||||
import time
|
||||
import os
|
||||
import numpy as np
|
||||
import torch
|
||||
from PIL import Image
|
||||
@@ -14,7 +15,14 @@ class VectorEngineImageGenerator:
|
||||
"""
|
||||
|
||||
def __init__(self):
|
||||
self.api_key = "sk-RZBLe4v8MolmD3fwOd6vdRTCaj7PohDhf4f44UNgWHEAA4zF"
|
||||
# Read API key from environment variable
|
||||
self.api_key = os.getenv("VECTOR_ENGINE_API_KEY")
|
||||
if not self.api_key:
|
||||
raise ValueError(
|
||||
"VECTOR_ENGINE_API_KEY environment variable is not set. "
|
||||
"Please set it before using this node: "
|
||||
"export VECTOR_ENGINE_API_KEY='your-api-key-here'"
|
||||
)
|
||||
|
||||
@classmethod
|
||||
def INPUT_TYPES(cls):
|
||||
|
||||
Reference in New Issue
Block a user