image-generate
Generate images using Seedream models. Invoke when user wants to create images from text prompts or reference images.
- Installs
- 893
- Last 24h
- —
- Trending rank
- —
- Security
- Not audited
Install
Works with every agent the skills CLI supports.
npx skills add https://skills.volces.com --skill image-generate- 01
Install
Run the command in your project. The CLI asks which agents to install for.
- 02
Describe the task
Ask your agent for something this skill covers. It loads image-generate automatically when relevant.
- 03
Review the result
The agent follows the SKILL.md steps, scripts and references bundled with the skill.
SKILL.md
The instructions your agent reads when the skill is triggered.
Image Generate Skill
This skill generates images using Doubao Seedream 4.0/4.5/5.0 models.
Trigger Conditions
- User wants to generate images from text descriptions
- User wants to create images based on reference images
- User asks for image generation capabilities
Usage
Environment Variables
Before using this skill, ensure the following environment variables are set:
ARK_API_KEYorMODEL_IMAGE_API_KEYorMODEL_AGENT_API_KEY: API key for the image generation serviceMODEL_IMAGE_API_BASE: API base URL (optional, has default)MODEL_IMAGE_NAME: Model name (optional, has default)
Function Signature
async def image_generate(
tasks: list[dict],
timeout: int = 600,
model_name: str = None,
) -> Dict:
Parameters
tasks (list[dict])
A list of image-generation tasks. Each task is a dict with the following fields:
Required:
prompt(str): Text description of the desired image(s). Chinese or English both work. To specify the number of images, add "生成N张图片" in the prompt.
Optional:
-
size(str): Image size. Two formats:- Resolution level: "1K", "2K", "4K"
- Exact dimensions: "<width>x<height>", e.g., "2048x2048", "2384x1728"
- Default: "2048x2048"
-
response_format(str): Return format. "url" (default, URL expires in 24h) or "b64_json" -
watermark(bool): Add watermark. Default: true -
image(str | list[str]): Reference image(s) as URL or Base64- For single image tasks: pass a string (exactly 1 image)
- For group image tasks: pass an array (2-10 images)
-
sequential_image_generation(str): Control group image generation. Default: "disabled"- Set to "auto" to generate multiple images
-
max_images(int): Maximum number of images for group generation. Range [1, 15] -
tools(list[dict]): Tool configuration, e.g.,[{"type": "web_search"}] -
output_format(str): Output format. "png" or "jpeg". Default: "jpeg"
Task Types
The model infers the task type from parameters:
- Text to Single Image: No
image,sequential_image_generationnot set or "disabled" - Text to Group Images: No
image,sequential_image_generation="auto" - Single Image to Single Image:
image=string,sequential_image_generationnot set or "disabled" - Single Image to Group Images:
image=string,sequential_image_generation="auto" - Multi Image to Single Image:
image=array (2-10),sequential_image_generationnot set or "disabled" - Multi Image to Group Images:
image=array (2-10),sequential_image_generation="auto"
Return Value
Script Return Info
The image_generate.py script will return these info:
{
"status": "success" | "error",
"success_list": [{"name": "image_name", "url": "image_url", "local_path": "local_path"}],
"error_list": ["image_name"],
"error_detail_list": [{"task_idx": 0, "error": {...}}]
}
Based on the script return info, the final response returned to the user consists of a description of the image generation task and the image URL(s) and local path(s). You may download the image from the URL, but the image URL should still be provided to the user for viewing and downloading.
Note: the URL is the 'url' in the success_list of script return info.
Final Return Info
You should return three types of information:
- File format, return the image file (if you have some other methods to send the image file) and the local path of the image, for example: local_path: /root/.openclaw/workspace/skills/image-generate/xxx.png
- After generation， show list of images with Markdown format, for example：
Code Implementation
See scripts/image_generate.py for the full implementation.
Example Usage
# Text to single image
python scripts/image_generate.py -p "A beautiful sunset over the ocean" -s 2048x2048
# Text to group images (generate 3 images)
python scripts/image_generate.py -p "生成3张可爱的小猫图片" -s 2K -g --max-images 3
# Image to image
python scripts/image_generate.py -p "Convert this image to anime style" -i "https://example.com/image.jpg"
# Multi-image to group images
python scripts/image_generate.py -p "Combine these images into a collage" --images "https://example.com/img1.jpg" "https://example.com/img2.jpg" -g --max-images 5
# Use specific model
python scripts/image_generate.py -p "A futuristic city" -m doubao-seedream-5-0-260128
# No watermark
python scripts/image_generate.py -p "A beautiful landscape" --no-watermark
# Output as PNG
python scripts/image_generate.py -p "A portrait photo" --output-format png
Command Line Options
| Option | Short | Description |
|---|---|---|
--prompt | -p | Text description of the desired image(s) (required) |
--size | -s | Image size (default: 2048x2048) |
--model | -m | Model name (default: doubao-seedream-4-0-250828) |
--image | -i | Single reference image URL |
--images | Multiple reference image URLs (space-separated) | |
--group | -g | Enable group image generation |
--max-images | Max images for group generation (default: 15) | |
--output-format | Output format: png or jpeg (default: jpeg) | |
--timeout | -t | Timeout in seconds (default: 600) |
--no-watermark | Disable watermark |
Model Fallback
If you encounter a model-related error (like ModelNotOpen), you can downgrade to these models:
doubao-seedream-5-0-260128doubao-seedream-4-5-251128doubao-seedream-4-0-250828
Error Handling
- IF the script raises the error "PermissionError: ARK_API_KEY or MODEL_IMAGE_API_KEY or MODEL_AGENT_API_KEY not found in environment variables", inform the user that they need to provide the
ARK_API_KEYorMODEL_IMAGE_API_KEYorMODEL_AGENT_API_KEYenvironment variable. Write it to the environment variable file in the workspace. If the file already exists, append it to the end. Ensure the environment variable format is correct, make the environment variable effective, and retry the image generation task that just failed.
Notes
- Group image tasks require
sequential_image_generation="auto" - To specify the number of group images, add the count in the prompt (e.g., "生成3张图片")
- Recommended sizes: 2048x2048 or standard aspect ratios for best quality
- URL responses expire in 24 hours
FAQ
What does the image-generate skill do?
Generate images using Seedream models. Invoke when user wants to create images from text prompts or reference images.
How do I install image-generate?
Run npx skills add https://skills.volces.com --skill image-generate in your project. The skills CLI detects the agents you use and copies the skill into the right folder. For Claude Code you can also place the skill folder at ~/.claude/skills/image-generate/ (personal) or .claude/skills/image-generate/ (project).
Which AI agents can use image-generate?
Any agent that supports the open Agent Skills format (a folder with a SKILL.md file), including Claude Code, Codex, Cursor, GitHub Copilot, Gemini CLI, Windsurf, Cline, OpenCode and more.
Is image-generate safe to install?
No partner security audit is available yet. Skills can run commands and scripts, so read the SKILL.md and any bundled files before installing.
Who maintains image-generate?
It is published by skills.volces.com in skills.volces.com. It has 893 recorded installs.
More from skills.volces.com
byted-web-search
skills.volces.com
火山引擎豆包搜索 API（原联网搜索/融合信息搜索），返回网页/图片结果。联网搜索场景优先使用本 skill。触发词包括：豆包搜索、查/搜/找、真的吗/靠谱吗/确认/核实、最近/今天/最新/近期、出处/来源/链接、Agent Plan、融合信息搜索、Harness、有什么/有哪些/推荐、价格/政策/汇率/行情、对比/区别/哪个好、听说/据说/不太确定、热搜/热门/火、帮我看/了解一下、求证/辟谣、值不值得/该不该。任务依赖在线事实或时效性时优先使用。若回答可能依赖外部事实，优先调用本 skill 再作答。
byted-supabase
skills.volces.com
火山引擎 Supabase . 管理 AIDAP Supabase 项目、工作区、数据库、分支、Auth、Realtime、Edge Functions、Storage、API Keys、SQL、Schema 变更、TypeScript 类型生成和 MCP 集成。
find-skills
skills.volces.com
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.
byted-util-ark-cua
skills.volces.com
Delegate broad computer-use tasks to ARK CUA for Volcengine AgentPlan users through an authenticated cloud desktop, and synchronize explicit credentials to a caller-owned CUA through Credential Agent. Use for web or desktop-app operation, file workflows, reusable task contexts, artifacts, temporary CUA App URLs, desktop shutdown/start/recovery, inspection, or exact browser, environment, secret, Credential Set, and managed-file credential setup/sync/status/reset. Do not use when local reasoning or a purpose-built local/API tool can complete the request more directly.
agent-browser
skills.volces.com
Headless browser automation CLI optimized for AI agents with accessibility tree snapshots and ref-based element selection
self-improving-agent
skills.volces.com
AI自我改进与记忆系统 - 解决'同类错误反复犯、用户纠正不长记性'的痛点。自动捕获错误、用户纠正、最佳实践，并转化为长期记忆。
Popular media & creative skills
hyperframes
heygen-com/hyperframes
Read first to make, edit, animate or render any video with HyperFrames (HTML rendered to video), including launch films, explainers, music videos, charts, maps, vertical clips, title cards, captions and overlays. Holds the render contract, the work loop and what each kind of video needs.
media-use
heygen-com/hyperframes
Get or make any media for a HyperFrames video - music, sound effects, images, icons, logos, voiceover, avatar and generated video, transcripts, cutouts, colour grades and looks - with HeyGen or free local tools, and mix placed audio. Also for footage that looks dark, flat or dull, or should be stylized or hidden.
hyperframes-registry
heygen-com/hyperframes
About 450 ready-made HyperFrames blocks and components installed as editable source - transitions, overlays, titles, kinetic type, captions, charts, map overlays, 3D, camera moves. Use it before hand-building any named visual (CRT scanlines, glitch, film grain, a chart); also for hyperframes add and catalog.
hyperframes-creative
heygen-com/hyperframes
Non-animation creative direction for HyperFrames videos. Use for design spec (frame.md / design.md) handling, palettes, typography, narration, beat planning, audio-reactive visuals, composition patterns, and brand / style decisions. For atomic motion patterns and scene blueprints, use hyperframes-animation.
ai-video-generation
101-skills/superpowers
Generate AI videos with Google Veo, Seedance 2.0, HappyHorse, Wan, Grok and 40+ models via inference.sh CLI. Models: Veo 3.1, Veo 3, Seedance 2.0, HappyHorse 1.0, Wan 2.5, Grok Imagine Video, OmniHuman, Fabric, HunyuanVideo. Capabilities: text-to-video, image-to-video, reference-to-video, video editing, lipsync, avatar animation, video upscaling, foley sound. Use for: social media videos, marketing content, explainer videos, product demos, AI avatars. Triggers: video generation, ai video, text to video, image to video, veo, animate image, video from image, ai animation, video generator, generate video, t2v, i2v, ai video maker, create video with ai, runway alternative, pika alternative, sora alternative, kling alternative, seedance, happyhorse
ai-image-generation
101-skills/superpowers
Generate AI images with GPT-Image-2, FLUX, Gemini, Grok, Seedream, Reve and 50+ models via inference.sh CLI. Models: GPT-Image-2, FLUX Dev LoRA, FLUX.2 Klein LoRA, Gemini 3 Pro Image, Grok Imagine, Seedream 4.5, Reve, ImagineArt. Capabilities: text-to-image, image-to-image, inpainting, LoRA, image editing, upscaling, text rendering. Use for: AI art, product mockups, concept art, social media graphics, marketing visuals, illustrations. Triggers: flux, image generation, ai image, text to image, stable diffusion, generate image, ai art, midjourney alternative, dall-e alternative, text2img, t2i, image generator, ai picture, create image with ai, generative ai, ai illustration, grok image, gemini image, gpt image, openai image, chatgpt image