Seedream Image
Documentsseedream-imageSeedream Image is an Agent Skill for documents published in the majiayu000/claude-skill-registry repository on GitHub: a SKILL.md instruction file an AI agent can load to do this task.
Generate and edit AI images with Seedream (ByteDance) via AceDataCloud API. Use when creating images from text prompts, editing existing images with inpainting/outpainting, or working with ultra-high-resolution outputs. Supports Seedream 2.0, 2.1, 3.0, and 3.0 Turbo models.
How to use this skill
Bring this guide into your coding agent with a prompt tailored to the tool you use.
- Open your project in Codex.
- Copy and paste the prompt below.
- Review files and risks before approving any action.
Inspect the Agent Skill at https://github.com/majiayu000/claude-skill-registry/blob/HEAD/skills/ai-ml/seedream-image-acedatacloud-skills-2/SKILL.md and all supporting files. Report provenance, permissions, scripts, dependencies, and security risks. Propose an exact installation into .agents/skills/seedream-image, but wait for my approval before writing files or running scripts.
Copying this prompt does not install or run the skill. Review third-party files before use.
Seedream Image Generation
Generate and edit AI images through AceDataCloud's Seedream (ByteDance) API.
Authentication
export ACEDATACLOUD_API_TOKEN="your-token-here"
Quick Start
curl -X POST https://api.acedata.cloud/seedream/images \
-H "Authorization: Bearer $ACEDATACLOUD_API_TOKEN" \
-H "Content-Type: application/json" \
-d '{"prompt": "a cyberpunk cat wearing VR goggles in a neon city", "model": "seedream-3.0"}'
Models
| Model | Resolution | Speed | Best For |
|---|---|---|---|
seedream-2.0 | Standard | Fast | Quick drafts |
seedream-2.1 | Standard | Fast | Improved quality over 2.0 |
seedream-3.0 | Up to 2048×2048 | Standard | High-quality generation (default) |
seedream-3.0-turbo | Up to 2048×2048 | Faster | Speed-optimized with near-3.0 quality |
Workflows
1. Text-to-Image
POST /seedream/images
{
"prompt": "a serene Japanese garden with cherry blossoms and a red bridge",
"model": "seedream-3.0",
"width": 1024,
"height": 1024
}
2. Image Editing (Inpainting / Outpainting)
Edit regions of an existing image using a mask.
POST /seedream/images/edit
{
"prompt": "replace with a golden sunset sky",
"image_url": "https://example.com/photo.jpg",
"mask_url": "https://example.com/mask.png",
"model": "seedream-3.0"
}
Parameters
Generation
| Parameter | Values | Description |
|---|---|---|
model | "seedream-2.0", "seedream-2.1", "seedream-3.0", "seedream-3.0-turbo" | Model to use |
width | 512 – 2048 | Image width in pixels |
height | 512 – 2048 | Image height in pixels |
seed | integer | Seed for reproducible results |
Editing
| Parameter | Required | Description |
|---|---|---|
image_url | Yes | URL of the source image to edit |
mask_url | Yes | URL of the binary mask (white = edit region) |
prompt | Yes | Describe what to place in the masked area |
MCP Server
pip install mcp-seedream
Or hosted: https://seedream.mcp.acedata.cloud/mcp
Key tools: seedream_generate_image, seedream_edit_image
Gotchas
- Maximum resolution is 2048×2048 — exceed this and requests fail
- Mask images must be binary (black/white) with the same dimensions as the source image
seedream-3.0-turbooffers a good speed/quality trade-off for iterative workflows- Results return a direct image URL — no task polling needed for generation
- Editing always requires both
image_urlandmask_url