seedream-5-lite

⛔ Seedream 5.0 lite（Delisted · Do not use）

🔴 This capability has been delisted, and this Skill is now 100% uncallable.

• The platform capability seedream-lite was delisted on 2026-08-10 (success rate before delisting was 0%).
• POST https://doubaoya.com/api/skills/seedream-lite/invoke Toany caller it always returns 503 CAPABILITY_UNAVAILABLE(it is blocked before authentication and billing, sono points will be deducted）。
• Retrying is meaningless; changing the key, parameters, or network will not help.

✅ To generate images, switch to image-gen Skill(Doubaoya GPT-image2, POST /api/skills/gpt-image-gen/invoke, currently available). For WeChat public account covers, use wechat-cover。

This document is retained only to preserve the historical contract and the delisting conclusion—do not send requests based on it. If this capability is relisted in the future,GET /api/skills will show seedream-liteagain, and this banner can be deleted then.

---

This duck helps you generate images with Seedream 5.0 lite in one command—give it a prompt and it generates an image, coveringtext-to-image / image-to-image / image sets / prompt optimization, and you can also specify the size. No need to build your own image generation pipeline; pay per use and get direct image links back.

Calls go through doubaoya.com in one line, with authentication using your own key (environment variable DOUBAOYA_API_KEY, in the form dyh_…）。

⏳ This is an asynchronous slow operation: the image is generated server-side, about 6 minutes, and it is returned in one go within a single request—no client-side polling needed; just send one POST and wait for the result.

---

Use cases

Scenario	How to use	What you get
Text-to-image	Provide only one prompt	Direct link to the image generated from the description
Image sets / multiple images	Use the prompt to describe a series of scenes	A batch of images with a consistent style
Specify size	Add --size to set width and height	An image with the target aspect ratio
Make covers / illustrations	Describe the style and subject	Ready-to-use asset images

---

Workflow (3 steps)

1. Write a prompt (optionally specify size)

Convert the user's needs into a clear image prompt, and determine the size if necessary (default 2048x2048）。

2. Call the script (wait patiently for a few minutes)

python3 "$SKILL_PATH/scripts/generate_image.py" "一只戴礼帽的鸭子站在复古海报里，极简平面风"

Specify size:

python3 "$SKILL_PATH/scripts/generate_image.py" "夏日柠檬汽水广告主视觉" --size 2048x2048

The script will first print on stderr “submitted, generating server-side”, thenwait about 6 minutesuntil the result is returned, printing the data from the success envelope as JSON to stdout.Run the script only once per image generation; do not interrupt it midway and do not call it repeatedly.

3. Render the image

From data.images(URL array), take the address and dodefensive reading— The array may be empty or missing; if it is missing, prompt that no image was obtained. Just give the user the direct image link.

---

Get the key (secret key)

1. Open doubaoya.com
2. Log in
3. Go to Key Center
4. Generate key(in the form dyh_…）

Configure it as an environment variable (the script only recognizes this one):

export DOUBAOYA_API_KEY="dyh_你的密钥"

Iron rule: never print the key, never write it to a file, never echo it back to the user. The script itself also never outputs the key. All requests are sent only to doubaoya.com。

---

Interface and envelope

• POST https://doubaoya.com/api/skills/seedream-lite/invoke
• Auth header:Authorization: Bearer $DOUBAOYA_API_KEY
• Request body:{ "prompt": "<提示词>", "size": "2048x2048" }
  • prompt: string, required
  • size: string WxH, optional (default 2048x2048, controlled by --size )
• Asynchronous slow operation: the server completes generation within about 6 minutes and returns it in this request; no polling is needed.
• Return envelope:

  {
    "success": true,
    "requestId": "...",
    "data": { "images": [ "https://...png" ] },
    "error": null
  }
  

• First check success: only if it is true should you read data; otherwise read error.code / error.message。

---

Error handling

When the script fails, it prints to stderr [error] CODE: message and exits with exit code 1. Common cases:

HTTP	code	Meaning	Handling
503	CAPABILITY_UNAVAILABLE	Capability has been taken offline (the current actual return)	Do not retry, switch to image-gen Skill
401	MISSING_API_KEY / UNAUTHORIZED	No key provided or invalid key	Check DOUBAOYA_API_KEY, go to the Key Center to regenerate
400	VALIDATION_ERROR	Invalid parameters (such as empty prompt, wrong size format)	Fix the parameters and retry
402	INSUFFICIENT_CREDITS	Insufficient quota	Go to doubaoya.com to top up/renew quota
502	PROVIDER_FAILED	Temporary upstream failure (automatically refunded）	Safe to retry

502 PROVIDER_FAILED will automatically refund; retrying is safe and will not double-charge. Butnow you will only get 503: the capability has been taken offline, and retrying will never succeed.

---

Directory structure

seedream-5-lite/
├── SKILL.md                # 本文件
└── scripts/
    └── generate_image.py   # 零依赖脚本（urllib），调用 doubaoya.com

About the notice field in the response

After calling the doubaoya API corresponding to this skill, if the notice field appears at the top level of the returned JSON, please relay this sentence to the user verbatim—this is a notice that this skill has an update, it does not affect the result of this call, and no retry or behavior change is needed.