Skip to main content
skill CX Codex

seedream-image — Claude Code skill: what it does, how to install

The seedream-image skill connects Seedream 5.0 for image generation, editing, streaming, and layer extraction. Use it for reference images, transparent backgrounds, or related image sets.

Apache-2.0 235 installs ★ 17 updated 2026-10-25

Install into Claude Code · Skills CLI (Vercel) All methods and platforms ↓
npx skills add AceDataCloud/Skills --skill seedream-image -a claude-code
Open on GitHub

What seedream-image does

seedream-image sends JSON requests to Seedream 5.0 through AceDataCloud. It can create images from prompts, edit a URL or Base64 image, produce related image sets, and return streamed results. The Lite model supports web search and sequential image generation; Pro handles transparent-background edits and editable layer extraction.

The skill documents REST calls, asynchronous task polling, streaming events, and optional tools from mcp-seedream-pro and seedream-cli. Layer extraction is Pro-only and accepts exactly one PNG or JPEG. URL results expire, so generated files need to be saved promptly.

Requests require ACEDATACLOUD_API_TOKEN. For asynchronous jobs, the documented flow is to keep polling the returned task_id rather than submitting the same billable request again.

What it helps with

  • generate an image from a text prompt
  • edit a picture with a reference image
  • produce a related image set
  • create a transparent PNG edit
  • split an image into editable layers

Example prompts for the agent

  • Use seedream-image to create four related images showing a courier crossing a rainy neon city.
  • Edit the image at this URL, replace the parrot with a peacock, and return a transparent PNG.
  • Use the Pro model to decompose poster.png and preserve each layer’s bounding box.

How to install seedream-image

1Skills CLI (Vercel)

npx skills add AceDataCloud/Skills --skill seedream-image -a claude-code

2Manually: put the files in place

~/.claude/skills/seedream-image/SKILL.md

Copy the whole skill folder; for one project use .claude/skills/seedream-image/

Step by step, with commands for each platform: How to install skills in Claude Code: five ways

Questions about seedream-image

How do I install seedream-image in Claude Code?

Run npx skills add AceDataCloud/Skills --skill seedream-image -a claude-code, then check ~/.claude/skills/seedream-image/SKILL.md.

What does seedream-image do?

It connects Claude Code to Seedream 5.0 through AceDataCloud for image generation, editing, streaming, related image sets, and editable layer extraction.

What does seedream-image require?

Set an AceDataCloud key in ACEDATACLOUD_API_TOKEN. Layer extraction requires the Pro model and exactly one PNG or JPEG input.

Source text

SKILL.md · Apache-2.0
---
name: seedream-image
description: Generate, edit, stream, or decompose images with Seedream 5.0 via AceDataCloud. Use for text-to-image, reference-image editing, related image sets, transparent-background edits, or editable layer extraction.
license: Apache-2.0
metadata:
  author: acedatacloud
  version: "1.1"
compatibility: Requires ACEDATACLOUD_API_TOKEN (get an API key at https://platform.acedata.cloud/console/applications). Optionally pair with mcp-seedream-pro or seedream-cli.
---

# Seedream Image

Use `POST https://api.acedata.cloud/seedream/images`. Authenticate with `Authorization: Bearer $ACEDATACLOUD_API_TOKEN` and JSON request bodies.

## First-time setup

1. Install the official Skill with `clawhub install @acedatacloud/seedream`. Check that the ClawHub publisher is **@acedatacloud**.
2. Sign in at [AceDataCloud → Applications](https://platform.acedata.cloud/console/applications), open **General application**, and check Seedream access, balance, and current pricing. Copy its API key, or select **Manage Keys → Create** for a separate key. Copy the key value without `Bearer `; a `platform-...` management token is not a service API key.
3. If you enable **Allowed APIs** restrictions, include `/seedream/images` and `/seedream/tasks`. Advanced workflows below may call additional routes.
4. On the OpenClaw Gateway host, put `ACEDATACLOUD_API_TOKEN=your_api_key_here` in `~/.openclaw/.env`, then restart the Gateway and start a new session. For a direct terminal test, run `export ACEDATACLOUD_API_TOKEN="your_api_key_here"` in that shell. Never put the key in a prompt or commit an `.env` file.
5. Follow the **Generate or edit** example below. If this workflow returns a task ID, query that same task until it finishes; do not submit the same billable request again just to check progress.

[Illustrated key setup, first run, and troubleshooting](https://github.com/AceDataCloud/Skills#first-run-with-clawhub-and-openclaw) · [Token details](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/authentication.md)

## Pick the model from the requested capability

| Capability | Seedream 5.0 Pro | Seedream 5.0 Lite |
|---|---|---|
| Model ID | `doubao-seedream-5-0-pro-260628` | `doubao-seedream-5-0-lite-260128` |
| Generate/edit one image | Yes | Yes |
| Reference images | Up to 10 | Up to 14 |
| Related image set | No | Yes; input + output ≤ 15 |
| Streaming / web search | No | Yes |
| Layer decomposition / transparent background | Yes | No |
| Prompt optimization | `standard`, `fast` | `standard` |
| Preset sizes | `1K`, `1.5K`, `2K` | `2K`, `3K`, `4K` |

Seedream 4.5 and 4.0 remain available for compatibility. Do not send a parameter to a model that does not support it.

## Generate or edit

```bash
curl https://api.acedata.cloud/seedream/images \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-0-lite-260128",
    "prompt": "a four-panel storyboard of a courier crossing a rainy neon city",
    "size": "2K",
    "sequential_image_generation": "auto",
    "sequential_image_generation_options": {"max_images": 4},
    "watermark": false
  }'
```

For editing, add `image` as one URL/Base64 string or an array. `response_format` is `url` or `b64_json`; 5.0 Pro/Lite also support `output_format` as `jpeg` or `png`. Explicit dimensions use `WIDTHxHEIGHT` and must satisfy the selected model's pixel and aspect-ratio limits.

Use Lite web search only when current information matters:

```json
{"tools": [{"type": "web_search"}]}
```

## Transparent-background Pro edit

Use one transparent PNG input and PNG output:

```json
{
  "model": "doubao-seedream-5-0-pro-260628",
  "prompt": "replace the parrot with a peacock",
  "image": "https://example.com/layer.png",
  "background": "transparent",
  "output_format": "png",
  "size": "1.5K"
}
```

Do not combine `background` with layer decomposition. `transparent` with JPEG is invalid.

## Decompose an image into editable layers

`layer_decomposition` is Pro-only and requires exactly one PNG/JPEG. Omit `prompt` for automatic decomposition, describe desired elements in natural language, or use normalized `<bbox>` coordinates.

```bash
curl https://api.acedata.cloud/seedream/images \
  -H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "doubao-seedream-5-0-pro-260628",
    "image": "https://example.com/poster.png",
    "layer_decomposition": true,
    "size": "auto",
    "watermark": false
  }'
```

The response contains one base image (`z_index: 0`) and up to 16 transparent PNG layers. Each layer can include `name`, `description`, and `bounding_box.absolute`/`normalized`. To recompose, scale each layer to its bounding-box width and height, place it at left/top, and draw in ascending `z_index`. Any layer failure fails the whole decomposition.

## Async tasks

Generation can take time. Prefer `"async": true`; the response returns `task_id`. Poll using:

```json
POST /seedream/tasks
{"action": "retrieve", "id": "<task_id>"}
```

Follow [async task polling](https://github.com/AceDataCloud/Skills/blob/main/skills/_shared/async-tasks.md). Use `callback_url` only when a real public webhook exists. Do not use a health endpoint as a fake callback.

## Streaming

Lite/4.x support streaming. Send `"stream": true` with `Accept: application/x-ndjson`; read one normalized JSON event per line until `image_generation.completed`. Do not combine streaming with `async` or `callback_url`.

- `image_generation.partial_succeeded`: one generated image
- `image_generation.partial_failed`: one failed item; other Lite images may still succeed
- `image_generation.completed`: final usage and the only billing completion

## Agent tools

- MCP: `pip install mcp-seedream-pro`; use `seedream_generate_image`, `seedream_edit_image`, `seedream_decompose_image`, then poll with `seedream_get_task`.
- CLI: `pip install seedream-cli`; use `seedream generate`, `seedream edit`, `seedream decompose`, or `seedream generate --stream --json`.
- Hosted MCP: `https://seedream.mcp.acedata.cloud/mcp`.

MCP image tools are asynchronous, so use REST or CLI for real-time streaming.

## Result and billing safeguards

- URL results expire; persist files promptly.
- Lite `data[]` may mix successful images and per-item `error` objects. Count only successful images.
- Pro layer items are billed individually by actual output size; the base and every successful layer count separately.
- Preserve `z_index`, bounding boxes, item errors, `tools`, and `usage`; do not flatten the response to a URL list.
- Never estimate final billed cost from requested size alone. Use the returned `cost`/usage and the live pricing page: https://platform.acedata.cloud/services/seedream?tab=pricing.

© acedatacloud · Apache-2.0 · AceDataCloud/Skills

Similar skills

All skills for AI and ML →

From the same set67

The whole set →
flux-image flux-image is a Claude Code skill for generating and editing images through the AceDataCloud Flux API, including text-to-image, instruction-based edits, and FLUX 3 video. CX Codex +1 238installs wan-video wan-video generates AI videos from text prompts and animates images using Alibaba Wan models through the AceDataCloud API. CX Codex +1 238installs producer-music producer-music creates AI music through the AceDataCloud Producer API, including songs, lyrics, covers, and instrumentals. It also edits existing tracks and separates stems. CX Codex +1 236installs hailuo-video hailuo-video generates video from text or animates images via AceDataCloud's Hailuo (MiniMax) API. Supports text-to-video, image-to-video, and director mode for precise camera and motion control. CX Codex +1 235installs nano-banana-image nano-banana-image is a skill for generating and editing images through AceDataCloud's API, using text prompts and reference URLs with 1K, 2K, or 4K output. CX Codex +1 232installs tencentcloud-cos Manage Tencent Cloud COS buckets and objects from an agent: move files, inspect storage, create signed URLs, and remove objects. Useful for routine COS operations. CX Codex +1 232installs google-search google-search runs Google queries for pages, images, news, maps, places or videos through the AceDataCloud API and returns structured results to the agent. CX Codex +1 232installs google-gmail google-gmail is a Claude Code skill for searching Gmail, reviewing threads, and handling labels or attachments. Sending and other write actions require granted scopes and user confirmation. CX Codex +1 231installs

Project sponsors

Companies that keep this analytics open