Back to Details

krea-api

Compare original and translation side by side

🇺🇸

Original

English
🇨🇳

Translation

Chinese

Krea.ai Image Generation Skill

Krea.ai 图片生成Skill

Generate images using Krea.ai's API with support for multiple models including Flux, Imagen 4, Ideogram 3.0, and more.
通过Krea.ai的API生成图片，支持包括Flux、Imagen 4、Ideogram 3.0等在内的多种模型。

Features

功能特性

  • Async job-based generation (POST → poll → result)
  • Support for multiple image models
  • Configurable parameters (width, height, steps, guidance, seed, etc.)
  • Webhook support for background completion
  • Stdlib-only dependencies (no 
    requests
    required)
  • 基于异步任务的生成流程（POST请求 → 轮询 → 获取结果）
  • 支持多种图片生成模型
  • 可配置参数（宽度、高度、步数、引导系数、随机种子等）
  • 支持Webhook实现后台完成通知
  • 仅依赖Stdlib库（无需
    requests
    ）

Setup

配置步骤

  1. Get your Krea.ai API credentials from https://docs.krea.ai/developers/api-keys-and-billing
  2. Configure with:
bash
clawdbot config set skill.krea_api.key_id YOUR_KEY_ID
clawdbot config set skill.krea_api.secret YOUR_SECRET
  1. Or pass credentials directly as arguments.
  1. 从https://docs.krea.ai/developers/api-keys-and-billing获取你的Krea.ai API凭证
  2. 进行配置：
bash
clawdbot config set skill.krea_api.key_id YOUR_KEY_ID
clawdbot config set skill.krea_api.secret YOUR_SECRET
  1. 或者直接将凭证作为参数传入。

Usage

使用方法

Interactive Mode

交互模式

You: Generate a sunset over the ocean with Flux
Klawf: Creates the image and returns the URL
你：用Flux生成一张海上日落的图片
Klawf：创建图片并返回URL

Python Script

Python脚本

python
from krea_api import KreaAPI

api = KreaAPI(
    key_id="your-key-id",
    secret="your-secret"
)
python
from krea_api import KreaAPI

api = KreaAPI(
    key_id="your-key-id",
    secret="your-secret"
)

Generate and wait

生成并等待结果

urls = api.generate_and_wait( prompt="A serene Japanese garden", model="flux", width=1024, height=1024 ) print(urls)
undefined
urls = api.generate_and_wait( prompt="宁静的日式庭院", model="flux", width=1024, height=1024 ) print(urls)
undefined

Available Models (examples)

可用模型（示例）

ModelEndpoint
flux
/generate/image/bfl/flux-1-dev
flux-kontext
/generate/image/bfl/flux-1-dev-kontext
flux-1.1-pro
/generate/image/bfl/flux-1-1-pro
imagen-3
/generate/image/google/imagen-3
imagen-4
/generate/image/google/imagen-4
ideogram-3.0
/generate/image/ideogram/ideogram-3-0
seedream-4
/generate/image/seedream/seedream-4
For the full list, run:
bash
python3 krea_api.py --list-models
模型接口地址
flux
/generate/image/bfl/flux-1-dev
flux-kontext
/generate/image/bfl/flux-1-dev-kontext
flux-1.1-pro
/generate/image/bfl/flux-1-1-pro
imagen-3
/generate/image/google/imagen-3
imagen-4
/generate/image/google/imagen-4
ideogram-3.0
/generate/image/ideogram/ideogram-3-0
seedream-4
/generate/image/seedream/seedream-4
查看完整模型列表，请运行：
bash
python3 krea_api.py --list-models

Parameters

参数说明

ParameterTypeDefaultDescription
promptstrrequiredImage description (max 1800 chars)
modelstr"flux"Model name from table above
widthint1024Image width (512-2368)
heightint1024Image height (512-2368)
stepsint25Generation steps (1-100)
guidance_scalefloat3.0Guidance scale (0-24)
seedstrNoneRandom seed for reproducibility
webhook_urlstrNoneURL for completion notification
参数类型默认值描述
prompt字符串必填图片描述（最多1800字符）
model字符串"flux"上述表格中的模型名称
width整数1024图片宽度（512-2368）
height整数1024图片高度（512-2368）
steps整数25生成步数（1-100）
guidance_scale浮点数3.0引导系数（0-24）
seed字符串None用于结果复现的随机种子
webhook_url字符串None用于接收完成通知的URL

Credits

致谢

Thanks to Claude Opus 4.5 for researching the correct API structure. The docs incorrectly suggest 
/v1/images/flux
but the working endpoint is 
/generate/image/bfl/flux-1-dev
.
感谢Claude Opus 4.5协助研究正确的API结构。官方文档错误地建议使用
/v1/images/flux
，而实际可用的接口地址是
/generate/image/bfl/flux-1-dev
。