eachlabs-image-generation

这段内容是审核时保存的快照。外部来源才是完整且最新的版本。

---
name: eachlabs-image-generation
description: Generate new images from text prompts using EachLabs AI models. Supports text-to-image with multiple model families including Flux, GPT Image, Gemini, Imagen, Seedream, and more. Use when the user wants to create new images from text. For editing existing images, see eachlabs-image-edit.
metadata:
  author: eachlabs
  version: "1.0"
---

# EachLabs Image Generation

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.

## Authentication

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

Set the `EACHLABS_API_KEY` environment variable. Get your key at [eachlabs.ai](https://eachlabs.ai).

## Quick Start

### 1. Create a Prediction

```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

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

Poll until `status` is `"success"` or `"failed"`. The output image URL is in the response.

## Model Selection Guide

### Text-to-Image

| 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 |
| GPT Image v2 | `gpt-image-v2-text-to-image` | Highest-fidelity OpenAI model, strong in-image text |
| 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 |

### Training

| 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 |

## Prediction Flow

1. **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.
2. **POST** `https://api.eachlabs.ai/v1/prediction` with model slug, version `"0.0.1"`, and input parameters matching the schema
3. **Poll** `GET https://api.eachlabs.ai/v1/prediction/{id}` until status is `"success"` or `"failed"`
4. **Extract** the output image URL(s) from the response

## Examples

### Text-to-Image with Flux 2 Turbo

```bash
curl -X POST https://api.eachla