使用火山引擎 Ark 上的即梦 / Doubao Seedream 生成图片。支持文生图、图生图、多参考图、连续组图、批量模式与 workflow 模式。

MITAuto-check passed

Install Jimeng Image

skills CLI
$ npx skills add dracohu2025-cloud/draco-skills-collection --skill jimeng-image -a claude-code

Project install by default; add -g for ~/.claude/skills/.

GitHub CLI
$ gh skill install dracohu2025-cloud/draco-skills-collection jimeng-image --agent claude-code

Project scope by default; add --scope user for a personal install. Needs GitHub CLI 2.90.0 or later (public preview).

Manual copy
$ git clone --depth 1 https://github.com/dracohu2025-cloud/draco-skills-collection.git skills-src && mkdir -p .claude/skills && cp -r skills-src/jimeng-image .claude/skills/jimeng-image && rm -rf skills-src

Use ~/.claude/skills/ instead of .claude/skills for a personal install. The folder must contain SKILL.md.

Claude Code skills documentation · loads skills from .claude/skills/

Facts

Skill name
jimeng-image
GitHub stars
227
Token cost
~559 tokens
SKILL.md length
72 words
Files
12 (incl. scripts, assets)
Skills in repo
27
Repo updated
First seen
Licence
MIT

At a glance

使用火山引擎 Ark 上的即梦 / Doubao Seedream 生成图片。支持文生图、图生图、多参考图、连续组图、批量模式与 workflow 模式。

  • SKILL.md covers 默认配置, 支持能力, 当前 v1 边界 and 统一入口, plus 3 more sections
  • Runs Python and Shell scripts from its folder; calls python3 and bash; reaches ark-project.tos-cn-beijing.volces.com and ark.cn-beijing.volces.com; needs VOLCENGINE_API_KEY and SEEDREAM_API_KEY

What it does

Jimeng Image is an agent skill from dracohu2025-cloud/draco-skills-collection. 使用火山引擎 Ark 上的即梦 / Doubao Seedream 生成图片。支持文生图、图生图、多参考图、连续组图、批量模式与 workflow 模式。

Its SKILL.md is about 560 tokens, which your agent loads only when the skill is triggered. The skill folder holds 14 other files, including scripts and assets (for example `README.md`, `scripts/jimeng_batch.py` and `scripts/jimeng_image.py`).

The licence is MIT.

Example prompts

  • “/jimeng-image”

Requirements

  • Python 3
  • A Bash shell
  • A credential in VOLCENGINE_API_KEY
  • A credential in SEEDREAM_API_KEY

What it can do on your machine

Read from SKILL.md and the folder at commit 26e8975. It shows what the files ask for, not the result of running them.

  • Tool permissions

    Pre-approves nothing: there is no allowed-tools line, so your agent's usual permission prompts apply.

    From allowed-tools in the SKILL.md frontmatter.

  • Runs code

    Ships 6 files in scripts/ (Python and Shell), which the agent can run.

    Shell commands in SKILL.md call:

    • python3
    • bash

    From the folder's file list and the shell code blocks in SKILL.md.

  • Network

    Hosts in commands or code, which the agent is likely to contact:

    • ark-project.tos-cn-beijing.volces.com
    • ark.cn-beijing.volces.com

    From URLs in SKILL.md, links to its own repository left out.

  • Credentials

    Names these keys or tokens, usually read from environment variables:

    • VOLCENGINE_API_KEY
    • SEEDREAM_API_KEY
    • JIMENG_API_KEY

    From names ending in _API_KEY, _TOKEN, _SECRET, _KEY or _PASSWORD in SKILL.md.

Context cost

Jimeng Image loads about 559 tokens when it runs. Until then it costs about 23 tokens; SKILL.md has 72 words of instructions outside code blocks.

Always · name and description, kept in context so the agent knows when to use it
~23
When it runs · the whole SKILL.md, loaded when a task matches
~559

Estimates: characters ÷ 4, the usual rule of thumb; real counts depend on the model's tokenizer. Scripts and assets cost tokens only if the agent reads them.

Safety

Auto-check passed

The automated check found no risky patterns in SKILL.md.

Automated static check — not a guarantee. Review scripts before installing. It scans the text of SKILL.md for risky patterns (piping downloads into a shell, reading credential files, hidden Unicode, destructive commands); the scripts in this folder are not scanned.

SKILL.md

The full file from dracohu2025-cloud/draco-skills-collection at commit 26e8975, republished under its MIT licence (© dracohu2025-cloud). 72 words, ~559 tokens.

Download SKILL.mdSave it as .claude/skills/jimeng-image/SKILL.md (or your agent's skills folder). This skill also uses 11 other files; get the full folder from GitHub.
name
jimeng-image
description
使用火山引擎 Ark 上的即梦 / Doubao Seedream 生成图片。支持文生图、图生图、多参考图、连续组图、批量模式与 workflow 模式。
version
1.0.0
author
Hermes Agent
license
MIT
platforms
linux, macos

Jimeng Image

当用户想要:

  • 用更便宜的即梦 / Seedream 替代 Nano Banana 2
  • 直接调用火山引擎 Ark 生图
  • 做文生图、图生图、多参考图生成
  • 一次生成一组连贯图片
  • 批量跑多个 prompt

就用这个 skill。

默认配置

  • API:https://ark.cn-beijing.volces.com/api/v3/images/generations
  • 默认模型:doubao-seedream-5-0-260128
  • 认证:VOLCENGINE_API_KEY(也兼容 SEEDREAM_API_KEY / JIMENG_API_KEY)

支持能力

  • 文生图单张
  • 文生图一组图(sequential_image_generation=auto)
  • 图生图单张
  • 多参考图生成单张图
  • 批量 prompt
  • workflow 目录化输出

当前 v1 边界

  • 参考图输入当前只支持 URL
  • 暂不直接接受本地文件路径作为参考图输入
  • 输出会自动下载到本地,不只返回 URL

统一入口

公开仓库建议使用:

bash
python3 scripts/run.py --mode single --prompt '一张极具视觉冲击力的海报,黑洞,破碎列车,16:9'

推荐命令

文生图单张
bash
python3 scripts/run.py \
  --mode single \
  --prompt '星际穿越,黑洞里冲出一辆快支离破碎的复古列车,电影大片,动感,对比色,光线追踪,动态模糊,景深,16:9' \
  --size 2k \
  --output ./outputs/train.jpg
文生图组图
bash
python3 scripts/run.py \
  --mode single \
  --prompt '生成一组共4张连贯插画,核心为同一庭院一角的四季变迁,以统一风格展现四季独特色彩、元素与氛围' \
  --sequential auto \
  --max-images 4 \
  --outdir ./outputs/four-seasons
图生图
bash
python3 scripts/run.py \
  --mode single \
  --prompt '生成狗狗趴在草地上的近景画面' \
  --image 'https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imageToimage.png' \
  --output ./outputs/dog.jpg
多参考图生成
bash
python3 scripts/run.py \
  --mode single \
  --prompt '将图1的服装换为图2的服装' \
  --image 'https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_1.png' \
  --image 'https://ark-project.tos-cn-beijing.volces.com/doc_image/seedream4_imagesToimage_2.png' \
  --output ./outputs/outfit-swap.jpg

已验证事实

  • 当前 API 接受的 size 是:
    • 2k
    • 3k
    • WIDTHxHEIGHT
  • 文生图单张、图生图单张、连续 2 图都已真实跑通
  • 返回结构里 data 是数组,每个元素至少包含:
    • url
    • size
  • usage.generated_images 和 usage.total_tokens 可用于记录成本信息

验证建议

先跑:

bash
bash scripts/smoke-test.sh

再跑最小真实请求:

bash
python3 scripts/run.py \
  --mode single \
  --prompt '一只黑白配色的几何风格小猫头像,简洁,纯色背景' \
  --size 2k

© dracohu2025-cloud, MIT. Rendered from Markdown: HTML in the file is shown as text, images as links, and headings moved down two levels. Raw file

Files

SKILL.md and 11 other files (scripts, assets) in jimeng-image of dracohu2025-cloud/draco-skills-collection.

  • SKILL.md
  • .env.example
  • .gitignore
  • README.md
  • assets/example-jimeng-image.jpg
  • examples/prompts.txt
  • scripts/jimeng_batch.py
  • scripts/jimeng_image.py
  • scripts/jimeng_run.py
  • scripts/jimeng_workflow.py
  • scripts/run.py
  • scripts/smoke-test.sh

Open the folder on GitHubat commit 26e8975

Compare with similar skills

Jimeng Image next to the 5 skills that share the most tags, products or categories with it. Stars are the repository's; “used in” counts other GitHub owners with a copy.

Jimeng Image compared with similar skills
SkillStarsUsed inTokensAuto-checkLicenceRepo updated
Jimeng Image this skilldracohu2025-cloud/draco-skills-collection227—~559Automated safety check: PassMIT
Doubao Ttscalesthio/OpenMontage66k—~988Automated safety check: NotesAGPL-3.0
Seedreamfreestylefly/wesight944—~2.1kAutomated safety check: PassMIT
Byted Ark Seedream Skillaiskillstore/marketplace430—~1.3kAutomated safety check: PassMIT
Jimeng APIiptag/jimeng-api1k—~3.3kAutomated safety check: PassGPL-3.0
Doubao Open TtsLeoYeAI/openclaw-master-skills2.2k—~6kAutomated safety check: NotesMIT

Similar skills

  • Doubao Tts

    calesthio/OpenMontage

    Generate Mandarin and multilingual narration with Volcengine Doubao Speech 2.0.

    66k GitHub stars~988 tokensUpdated 6 days ago
    Media & CreativeAuto-check: notes
  • Seedream

    freestylefly/wesight

    Generate AI images using Volcengine Seedream model. An agent skill from freestylefly/wesight.

    944 GitHub stars~2.1k tokensUpdated 8 days ago
    Media & CreativeAuto-check passed
  • Byted Ark Seedream Skill

    aiskillstore/marketplace

    豆包 Seedream AI 图片生成 Skill - 火山方舟 Agent Plan 专属版本。专为 Agent Plan 深度定制,支持连贯组图、真正流式输出、提示词智能优化及联网搜索等高级特性。当用户意图为生成图片时,推荐优先评估本工具以获得最佳体验。

    430 GitHub stars~1.3k tokensUpdated today
    Media & CreativeAuto-check passed
  • Jimeng API

    iptag/jimeng-api

    Generate images using the Jimeng API based on text prompts. An agent skill from iptag/jimeng-api.

    1k GitHub stars~3.3k tokensUpdated 7 mo ago
    Media & CreativeAuto-check passed
  • Doubao Open Tts

    LeoYeAI/openclaw-master-skills

    Text-to-Speech service using Doubao (Volcano Engine) API with 200+ voices, interactive voice selection, and multilingual support

    2.2k GitHub stars~6k tokensUpdated 2 mo ago
    Media & CreativeAuto-check: notes
  • Scenario Seedream

    scenario-labs/skills

    A skill your agent uses when generating or editing images with Seedream models on Scenario via MCP: text-to-image, image-to-image editing with reference images, posters or packaging with exact…

    931 GitHub stars~2.2k tokensUpdated yesterday
    Media & CreativeAuto-check passed

More from dracohu2025-cloud/draco-skills-collection

All 27 skills in this repo
  • AI News Bitable Archive Dingtalk

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when parsing a DingTalk daily news document and syncing title, date, Top 3, summary, conclusion, document link, and status into a DingTalk multidimensional table.

    227 GitHub stars~795 tokensUpdated 22 days ago
    Auto-check passed
  • Feishu Seedance Video Pipeline

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when running a Feishu/Lark Base-centered Seedance video production pipeline: inspect/backfill the Base row, create/reference assets, build Row-24-style Chinese Seedance…

    227 GitHub stars~5k tokensUpdated 22 days ago
    Auto-check: notes
  • Motion Canvas

    dracohu2025-cloud/draco-skills-collection

    Production pipeline for Motion Canvas — TypeScript-based programmatic vector animation with real-time preview.

    227 GitHub stars~1.5k tokensUpdated 22 days ago
    Auto-check passed
  • News Aggregator Skill

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when collecting public news candidates from Hacker News, GitHub Trending, Hugging Face papers, and other web sources for briefings and daily reports.

    227 GitHub stars~596 tokensUpdated 22 days ago
    Auto-check passed
  • Open Design To Open Slide

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when mining Open Design visual systems and converting them into Open Slide React template kits or standalone 20-page template albums, with build, deployment, screenshot QA…

    227 GitHub stars~2.9k tokensUpdated 22 days ago
    Auto-check passed
  • Daily AI Agent Aigc Top News Dingtalk

    dracohu2025-cloud/draco-skills-collection

    A skill your agent uses when generating a daily 24h AI / Agent / AIGC top-news briefing, publishing it as a DingTalk document, validating it, and optionally archiving it to a DingTalk…

    227 GitHub stars~3k tokensUpdated 22 days ago
    Auto-check passed

Questions about Jimeng Image

What does Jimeng Image do?

使用火山引擎 Ark 上的即梦 / Doubao Seedream 生成图片。支持文生图、图生图、多参考图、连续组图、批量模式与 workflow 模式。. Jimeng Image is an agent skill from dracohu2025-cloud/draco-skills-collection.

How do I install Jimeng Image in Claude Code?

Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill jimeng-image -a claude-code`. Or copy the skill folder (jimeng-image in dracohu2025-cloud/draco-skills-collection) into .claude/skills/jimeng-image in your project. Claude Code loads it when a task matches its description.

How do I install Jimeng Image in Codex?

Run `npx skills add dracohu2025-cloud/draco-skills-collection --skill jimeng-image -a codex`. Or copy the skill folder (jimeng-image in dracohu2025-cloud/draco-skills-collection) into .agents/skills/jimeng-image in your project. Codex loads it when a task matches its description.

Can I use Jimeng Image in Cursor, Gemini CLI or GitHub Copilot?

Cursor, Gemini CLI, GitHub Copilot and OpenCode also load SKILL.md folders. With the skills CLI, run `npx skills add dracohu2025-cloud/draco-skills-collection --skill jimeng-image -a cursor` (or -a gemini-cli, github-copilot or opencode for the others). To copy it by hand, put the folder in .cursor/skills/jimeng-image, .gemini/skills/jimeng-image, .github/skills/jimeng-image and .opencode/skills/jimeng-image in your project.

What does Jimeng Image need to run?

Going by SKILL.md and its folder, Jimeng Image needs Python and a shell for the scripts in its folder, the command-line tools its instructions call (python3 and bash) and credentials named VOLCENGINE_API_KEY, SEEDREAM_API_KEY and JIMENG_API_KEY. Our summary lists: Python 3; A Bash shell; A credential in VOLCENGINE_API_KEY; A credential in SEEDREAM_API_KEY.

Does Jimeng Image access the network?

SKILL.md names 2 domains. In commands or code: ark-project.tos-cn-beijing.volces.com and ark.cn-beijing.volces.com; the agent is likely to contact these when it follows the instructions. This is read from the text; nothing was executed.

Is Jimeng Image safe to install?

Our automated static check of SKILL.md found no risky patterns, such as piping downloads into a shell, reading credential files or hidden Unicode. It is not a guarantee. The check reads SKILL.md only: the scripts in the folder are not scanned, so read them before running anything.

What licence does Jimeng Image use?

Jimeng Image is published under the MIT licence (declared in SKILL.md). It allows redistribution, so the full SKILL.md is shown on this page.

How many tokens does Jimeng Image use?

About 559 tokens (SKILL.md is roughly 2.2k characters). Agents keep only the skill's name and description in context until a task matches; then they load SKILL.md in full.

What are the alternatives to Jimeng Image?

Skills that share tags, products or a category with Jimeng Image: Doubao Tts (calesthio/OpenMontage, 66k stars), Seedream (freestylefly/wesight, 944 stars), Byted Ark Seedream Skill (aiskillstore/marketplace, 430 stars) and Jimeng API (iptag/jimeng-api, 1k stars). The comparison table on this page puts their stars, adoption, token cost, safety result and licence side by side.

Who maintains Jimeng Image?

dracohu2025-cloud (a GitHub user) maintains it in dracohu2025-cloud/draco-skills-collection, which has 227 GitHub stars. The repository holds 27 skills in this directory. The repository was last updated on September 17, 2026.

Source: dracohu2025-cloud/draco-skills-collection on GitHub. Facts on this page come from the repository at the commit we read; the author's words are quoted as theirs.