seedream-img-gen

This skill should be used when the user wants to generate images using Seedream, the image generation model from ByteDance on Volcengine platform. Triggers include requests like 用Seedream生成图片, seedream画图, generate image with seedream, 调用seedream, 用豆包画图, or any request to create, draw, or generate images via the Seedream API.

3,891 stars

byopenclaw

View on GitHub Installation ↓

Best use case

seedream-img-gen is best used when you need a repeatable AI agent workflow instead of a one-off prompt.

Teams using seedream-img-gen should expect a more consistent output, faster repeated execution, less prompt rewriting.

When to use this skill

You want a reusable workflow that can be run more than once with consistent structure.

When not to use this skill

You only need a quick one-off answer and do not need a reusable workflow.
You cannot install or maintain the underlying files, dependencies, or repository context.

Installation

Claude Code / Cursor / Codex

$curl -o ~/.claude/skills/seedream-img-gen/SKILL.md --create-dirs "https://raw.githubusercontent.com/openclaw/skills/main/skills/anpupil/seedream-img-gen/SKILL.md"

Manual Installation

Download SKILL.md from GitHub
Place it in .claude/skills/seedream-img-gen/SKILL.md inside your project
Restart your AI agent — it will auto-discover the skill

How seedream-img-gen Compares

Feature / Agent	seedream-img-gen	Standard Approach
Platform Support	Not specified	Limited / Varies
Context Awareness	High	Baseline
Installation Complexity	Unknown	N/A

Frequently Asked Questions

What does this skill do?

Where can I find the source code?

You can find the source code on GitHub using the link provided at the top of the page.

Related Guides

AI Agents for Marketing

Discover AI agents for marketing workflows, from SEO and content production to campaign research, outreach, and analytics.

AI Agents for Startups

Explore AI agent skills for startup validation, product research, growth experiments, documentation, and fast execution with small teams.

AI Agents for Coding

Browse AI agent skills for coding, debugging, testing, refactoring, code review, and developer workflows across Claude, Cursor, and Codex.

SKILL.md Source

# Seedream 图片生成 Skill

## 概述

本 Skill 帮助通过火山引擎方舟平台（Volcengine Ark）的 Seedream 系列模型生成图片，支持文生图（text-to-image）和图生图（image-to-image，Seedream 4.0+）。

---

## 前置条件

1. **获取 API Key**：前往 https://console.volcengine.com/ark 注册并获取 `ARK_API_KEY`
2. **开通模型**：在方舟平台「开通管理」页面开通所需模型
3. **安装依赖**（二选一）：
   - 官方 SDK：`pip install 'volcengine-python-sdk[ark]'`
   - OpenAI 兼容：`pip install openai`

---

## 核心工作流

### 1. 收集必要信息

在生成图片前，需要明确：
- **提示词**（prompt）：图片内容描述，支持中英文
- **模型选择**：默认使用 `doubao-seedream-3-0-t2i-250415`（详细模型列表见 `references/api_reference.md`）
- **图片尺寸**（可选）：如 `1024x1024`、`1792x1024`
- **输出路径**（可选）：保存图片的本地路径

如果用户未明确提到模型，默认使用 Seedream 4.0（`doubao-seedream-4-0-250828`）。

### 2. 检查环境

To verify the environment is ready, run:
```bash
echo $ARK_API_KEY
```

If the API key is missing, instruct the user to set it:
```bash
export ARK_API_KEY="your_api_key_here"
```

### 3. 调用生成脚本

Use the bundled script at `scripts/generate_image.py`:

```bash
# 基本用法（文生图）
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "一只可爱的橘猫坐在窗边看夕阳，写实摄影风格" \
  --output output.png

# 指定模型
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "a cyberpunk city at night" \
  --model doubao-seedream-4-0-250828 \
  --output output.png

# 指定尺寸
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "横版风景画，超宽屏" \
  --size 1792x1024 \
  --output landscape.png

# 生成多张
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "卡通风格的小动物" \
  --n 4 \
  --output animals.png

# 使用 OpenAI 兼容模式
python3 ~/.workbuddy/skills/seedream-image-gen/scripts/generate_image.py \
  --prompt "描述内容" \
  --sdk openai \
  --output result.png
```

### 4. 处理结果

- 脚本成功执行后会输出图片保存路径
- 生成的图片默认保存到当前工作目录，也可通过 `--output` 指定
- 使用 `url` 格式时，脚本会自动下载图片到本地

---

## 快速内联调用（不使用脚本）

如果希望直接生成代码调用，可用以下模板：

```python
import os
from volcenginesdkarkruntime import Ark

client = Ark(api_key=os.environ.get("ARK_API_KEY"))
resp = client.images.generate(
    model="doubao-seedream-3-0-t2i-250415",
    prompt="YOUR_PROMPT_HERE",
    response_format="url",
)

url = resp.data[0].url
print("图片 URL:", url)

# 下载图片
import urllib.request
urllib.request.urlretrieve(url, "output.png")
print("已保存至 output.png")
```

---

## 模型选择建议

| 场景 | 推荐模型 |
|------|---------|
| 通用文生图，快速稳定 | `doubao-seedream-3-0-t2i-250415` |
| 高质量图片，支持参考图 | `doubao-seedream-4-0-250828` |
| 最新最强效果 | `doubao-seedream-4-5-251128` |
| 极速轻量 | `doubao-seedream-5-0-lite` |

---

## 参考资源

- 详细 API 参数和代码示例：`references/api_reference.md`
- 生成脚本（支持命令行调用）：`scripts/generate_image.py`
- 官方文档：https://www.volcengine.com/docs/82379

Related Skills

🎨 Doubao Seedream & Seedance API Skill

3891

from openclaw/skills

> **Professional AI Generation Suite** - Powered by Doubao Seed Models

---

3891

from openclaw/skills

name: article-factory-wechat

Content & Documentation

humanizer

3891

from openclaw/skills

Remove signs of AI-generated writing from text. Use when editing or reviewing text to make it sound more natural and human-written. Based on Wikipedia's comprehensive "Signs of AI writing" guide. Detects and fixes patterns including: inflated symbolism, promotional language, superficial -ing analyses, vague attributions, em dash overuse, rule of three, AI vocabulary words, negative parallelisms, and excessive conjunctive phrases.

Content & Documentation

find-skills

3891

from openclaw/skills

Helps users discover and install agent skills when they ask questions like "how do I do X", "find a skill for X", "is there a skill that can...", or express interest in extending capabilities. This skill should be used when the user is looking for functionality that might exist as an installable skill.

General Utilities

tavily-search

3891

from openclaw/skills

Use Tavily API for real-time web search and content extraction. Use when: user needs real-time web search results, research, or current information from the web. Requires Tavily API key.

Data & Research

baidu-search

3891

from openclaw/skills

Search the web using Baidu AI Search Engine (BDSE). Use for live information, documentation, or research topics.

Data & Research

agent-autonomy-kit

3891

from openclaw/skills

Stop waiting for prompts. Keep working.

Workflow & Productivity

Meeting Prep

3891

from openclaw/skills

Never walk into a meeting unprepared again. Your agent researches all attendees before calendar events—pulling LinkedIn profiles, recent company news, mutual connections, and conversation starters. Generates a briefing doc with talking points, icebreakers, and context so you show up informed and confident. Triggered automatically before meetings or on-demand. Configure research depth, advance timing, and output format. Walking into meetings blind is amateur hour—missed connections, generic small talk, zero leverage. Use when setting up meeting intelligence, researching specific attendees, generating pre-meeting briefs, or automating your prep workflow.

Workflow & Productivity

self-improvement

3891

from openclaw/skills

Captures learnings, errors, and corrections to enable continuous improvement. Use when: (1) A command or operation fails unexpectedly, (2) User corrects Claude ('No, that's wrong...', 'Actually...'), (3) User requests a capability that doesn't exist, (4) An external API or tool fails, (5) Claude realizes its knowledge is outdated or incorrect, (6) A better approach is discovered for a recurring task. Also review learnings before major tasks.

Agent Intelligence & Learning

botlearn-healthcheck

3891

from openclaw/skills

botlearn-healthcheck — BotLearn autonomous health inspector for OpenClaw instances across 5 domains (hardware, config, security, skills, autonomy); triggers on system check, health report, diagnostics, or scheduled heartbeat inspection.

DevOps & Infrastructure