eachlabs-image-generation

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

EachLabs Image Generation

EachLabs 图像生成

Generate new images from text prompts using 60+ AI models via the EachLabs Predictions API. For editing existing images (upscaling, background removal, style transfer, inpainting, face swap, 3D), see the

eachlabs-image-edit

skill.

通过EachLabs Predictions API，利用60余种AI模型根据文本提示生成新图像。如需编辑现有图像（包括放大、背景移除、风格迁移、图像修复、人脸替换、3D处理等），请查看

eachlabs-image-edit

技能。

Authentication

身份验证

Header: X-API-Key: <your-api-key>

Set the

EACHLABS_API_KEY

environment variable. Get your key at eachlabs.ai.

Header: X-API-Key: <your-api-key>

设置

EACHLABS_API_KEY

环境变量。可前往eachlabs.ai获取您的密钥。

Quick Start

快速开始

1. Create a Prediction

1. 创建预测任务

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-2-turbo-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A serene Japanese garden with cherry blossoms, watercolor style",
      "image_size": "landscape_16_9",
      "num_images": 1,
      "output_format": "png"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-2-turbo-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A serene Japanese garden with cherry blossoms, watercolor style",
      "image_size": "landscape_16_9",
      "num_images": 1,
      "output_format": "png"
    }
  }'

2. Poll for Result

2. 轮询获取结果

bash

curl https://api.eachlabs.ai/v1/prediction/{prediction_id} \
  -H "X-API-Key: $EACHLABS_API_KEY"

Poll until

status

"success"

"failed"

. The output image URL is in the response.

bash

curl https://api.eachlabs.ai/v1/prediction/{prediction_id} \
  -H "X-API-Key: $EACHLABS_API_KEY"

持续轮询直到

status

变为

"success"

或

"failed"

。输出图像的URL将包含在响应结果中。

Model Selection Guide

模型选择指南

Text-to-Image

文本转图像

Model	Slug	Best For
Flux 2 Turbo	`flux-2-turbo-text-to-image`	Fast, high quality general purpose
Flux 2 Flash	`flux-2-flash-text-to-image`	Fastest Flux generation
Flux 2 Max	`flux-2-max-text-to-image`	Highest quality Flux
Flux 2 Klein 9B	`flux-2-klein-9b-base-text-to-image`	Balanced quality/speed
Flux 2 Pro	`flux-2-pro`	Pro quality
Flux 2 Flex	`flux-2-flex`	Flexible outputs
Flux 2 LoRA	`flux-2-lora`	LoRA-powered generation
XAI Grok Imagine	`xai-grok-imagine-text-to-image`	Creative and artistic
GPT Image v1.5	`gpt-image-v1-5-text-to-image`	High quality, transparent bg
Bytedance Seedream v4.5	`bytedance-seedream-v4-5-text-to-image`	Bytedance latest
Gemini 3 Pro Image	`gemini-3-pro-image-preview`	Google's latest
Imagen 4	`imagen4-preview`	Google Imagen 4
Imagen 4 Fast	`imagen-4-fast`	Fast Google quality
Reve	`reve-text-to-image`	Artistic text-to-image
Hunyuan Image v3	`hunyuan-image-v3-text-to-image`	Tencent's latest
Ideogram V3 Turbo	`ideogram-v3-turbo`	Text in images
Minimax	`minimax-text-to-image`	High quality
Wan v2.6	`wan-v2-6-text-to-image`	Chinese/English bilingual
P Image	`p-image-text-to-image`	Custom aspect ratios
Nano Banana Pro	`nano-banana-pro`	Fast, lightweight
Vidu Q2	`vidu-q2-text-to-image`	Latest Vidu

模型	标识（Slug）	适用场景
Flux 2 Turbo	`flux-2-turbo-text-to-image`	快速、高质量通用型
Flux 2 Flash	`flux-2-flash-text-to-image`	速度最快的Flux生成模型
Flux 2 Max	`flux-2-max-text-to-image`	最高质量的Flux模型
Flux 2 Klein 9B	`flux-2-klein-9b-base-text-to-image`	质量与速度平衡型
Flux 2 Pro	`flux-2-pro`	专业级质量
Flux 2 Flex	`flux-2-flex`	输出灵活型
Flux 2 LoRA	`flux-2-lora`	基于LoRA的生成模型
XAI Grok Imagine	`xai-grok-imagine-text-to-image`	创意艺术型
GPT Image v1.5	`gpt-image-v1-5-text-to-image`	高质量、透明背景
Bytedance Seedream v4.5	`bytedance-seedream-v4-5-text-to-image`	字节跳动最新模型
Gemini 3 Pro Image	`gemini-3-pro-image-preview`	Google最新模型
Imagen 4	`imagen4-preview`	Google Imagen 4
Imagen 4 Fast	`imagen-4-fast`	快速Google质量型
Reve	`reve-text-to-image`	艺术化文本转图像
Hunyuan Image v3	`hunyuan-image-v3-text-to-image`	腾讯最新模型
Ideogram V3 Turbo	`ideogram-v3-turbo`	图像中包含文字
Minimax	`minimax-text-to-image`	高质量型
Wan v2.6	`wan-v2-6-text-to-image`	中英双语支持
P Image	`p-image-text-to-image`	自定义宽高比
Nano Banana Pro	`nano-banana-pro`	快速轻量型
Vidu Q2	`vidu-q2-text-to-image`	最新Vidu模型

Training

模型训练

Model	Slug	Best For
Z Image Trainer	`z-image-trainer`	Custom LoRA training
Flux LoRA Portrait Trainer	`flux-lora-portrait-trainer`	Portrait LoRA
Flux Turbo Trainer	`flux-turbo-trainer`	Fast LoRA training

模型	标识（Slug）	适用场景
Z Image Trainer	`z-image-trainer`	自定义LoRA训练
Flux LoRA Portrait Trainer	`flux-lora-portrait-trainer`	人像LoRA训练
Flux Turbo Trainer	`flux-turbo-trainer`	快速LoRA训练

Prediction Flow

预测流程

Check model
```
GET https://api.eachlabs.ai/v1/model?slug=<slug>
```
— validates the model exists and returns the
```
request_schema
```
with exact input parameters. Always do this before creating a prediction to ensure correct inputs.
POST
```
https://api.eachlabs.ai/v1/prediction
```
with model slug, version
```
"0.0.1"
```
, and input parameters matching the schema

Poll

GET https://api.eachlabs.ai/v1/prediction/{id}

until status is

"success"

"failed"

Extract the output image URL(s) from the response

验证模型：调用
```
GET https://api.eachlabs.ai/v1/model?slug=<slug>
```
—— 验证模型是否存在，并返回包含确切输入参数的
```
request_schema
```
。创建预测任务前务必执行此步骤，确保输入参数正确。
创建预测：向
```
https://api.eachlabs.ai/v1/prediction
```
发送POST请求，携带模型标识、版本
```
"0.0.1"
```
以及符合schema的输入参数

轮询结果：调用

GET https://api.eachlabs.ai/v1/prediction/{id}

持续轮询，直到状态变为

"success"

或

"failed"

提取结果：从响应中获取输出图像的URL

Examples

示例

Text-to-Image with Flux 2 Turbo

使用Flux 2 Turbo进行文本转图像

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-2-turbo-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A red vintage Porsche 911 on a winding mountain road at golden hour, photorealistic",
      "image_size": "landscape_16_9",
      "num_images": 1,
      "output_format": "png"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "flux-2-turbo-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A red vintage Porsche 911 on a winding mountain road at golden hour, photorealistic",
      "image_size": "landscape_16_9",
      "num_images": 1,
      "output_format": "png"
    }
  }'

Text-to-Image with GPT Image v1.5

使用GPT Image v1.5进行文本转图像

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gpt-image-v1-5-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A minimalist logo for a coffee shop called Brew Lab, clean vector style",
      "background": "transparent",
      "quality": "high",
      "output_format": "png"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "gpt-image-v1-5-text-to-image",
    "version": "0.0.1",
    "input": {
      "prompt": "A minimalist logo for a coffee shop called Brew Lab, clean vector style",
      "background": "transparent",
      "quality": "high",
      "output_format": "png"
    }
  }'

Text-to-Image with Imagen 4

使用Imagen 4进行文本转图像

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "imagen4-preview",
    "version": "0.0.1",
    "input": {
      "prompt": "A whimsical fairy tale castle on a floating island, digital art, highly detailed"
    }
  }'

bash

curl -X POST https://api.eachlabs.ai/v1/prediction \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $EACHLABS_API_KEY" \
  -d '{
    "model": "imagen4-preview",
    "version": "0.0.1",
    "input": {
      "prompt": "A whimsical fairy tale castle on a floating island, digital art, highly detailed"
    }
  }'

Image Size Options

图像尺寸选项

Most Flux 2 and Wan models use these presets:

```
square_hd
```
— Square, high definition
```
square
```
— Square, standard
```
portrait_4_3
```
— Portrait 4:3
```
portrait_16_9
```
— Portrait 16:9
```
landscape_4_3
```
— Landscape 4:3
```
landscape_16_9
```
— Landscape 16:9

P Image models use aspect ratio strings:

1:1

16:9

9:16

4:3

3:4

3:2

2:3

custom

大多数Flux 2和Wan模型支持以下预设尺寸：

```
square_hd
```
—— 高清正方形
```
square
```
—— 标准正方形
```
portrait_4_3
```
—— 竖屏4:3
```
portrait_16_9
```
—— 竖屏16:9
```
landscape_4_3
```
—— 横屏4:3
```
landscape_16_9
```
—— 横屏16:9

P Image模型使用宽高比字符串：

1:1

16:9

9:16

4:3

3:4

3:2

2:3

custom

Prompt Tips

提示词技巧

Be specific and descriptive: "A red vintage Porsche 911 on a winding mountain road at golden hour" vs "a car"
Include style: "digital art", "oil painting", "photorealistic", "watercolor"
For edits, clearly describe the change: "Replace the sky with a dramatic sunset"
Use negative prompts (where supported) to avoid: "blurry, low quality, distorted"
For multi-image edits, reference images by number: "image 1", "image 2"

描述要具体详细：比如“黄金时段，蜿蜒山路上的红色复古保时捷911”优于“一辆汽车”
包含风格描述：比如“数字艺术”、“油画”、“写实摄影”、“水彩画”
若涉及编辑，明确描述修改内容：比如“将天空替换为壮观的日落”
（在支持的模型中）使用负面提示词避免不理想效果：比如“模糊、低质量、失真”
多图像编辑时，按编号引用图像：比如“image 1”、“image 2”

Parameter Reference

参数参考

See references/MODELS.md for complete parameter details for each model.

各模型的完整参数详情请查看references/MODELS.md。