Seedream Image

Generate and edit AI images with Seedream (ByteDance) via AceDataCloud API. Use when creating images from text prompts, editing existing images with inpainti...

Security Scan

The skill's runtime instructions are consistent with an image-generation client (it legitimately needs an API token), but the package metadata omits that required credential and the skill references an optional third-party pip package and external endpoints with no homepage — these inconsistencies warrant caution.

Purpose & Capability

The SKILL.md describes a Seedream (AceDataCloud) image-generation/editing client and the calls shown (curl to api.acedata.cloud) match that purpose. However, the registry metadata lists no required environment variables while the SKILL.md explicitly says the skill 'Requires ACEDATACLOUD_API_TOKEN' — metadata/manifest inconsistency.

Instruction Scope

Instructions are scoped to calling AceDataCloud endpoints and to providing an API token. They do not instruct the agent to read unrelated files, system credentials, or to exfiltrate local data. The only extra action is an optional pip install recommendation for 'mcp-seedream'.

Install Mechanism

This is an instruction-only skill (no install spec). It suggests 'pip install mcp-seedream' or using a hosted MCP URL; installing that package would install third-party code on the system — vet the package source before installing. No automatic downloads or extract steps are specified by the skill itself.

Credentials

The SKILL.md requires ACEDATACLOUD_API_TOKEN (expected for an API client) but the registry metadata lists no required env vars or primary credential. This mismatch is a red flag: the runtime needs a secret that the metadata does not declare. Ensure you only provide a token scoped to AceDataCloud and understand its permissions and data retention policy.

Persistence & Privilege

The skill does not request persistent 'always' inclusion, does not declare config paths, and does not attempt to modify other skills or agent-wide settings in the provided instructions.

What to consider before installing

Before installing or using this skill: 1) Note the SKILL.md requires ACEDATACLOUD_API_TOKEN but the package metadata does not declare it — treat that as an inconsistency and only provide a token you control and that is scoped/minimal. 2) The skill targets https://api.acedata.cloud and mentions an optional pip package (mcp-seedream). If you plan to 'pip install' that package, verify its origin (PyPI publisher, source repo, checksum) before installing. 3) The skill has no homepage and the owner ID is opaque; prefer skills with verifiable vendor information if you need to send sensitive images (PII). 4) Confirm AceDataCloud's billing, privacy, and data-retention policies — images you send may be stored or used according to their terms. 5) Ask the publisher to update registry metadata to list ACEDATACLOUD_API_TOKEN as a required credential and to provide a homepage/source repo; that fixes the main incoherence. If you need help vetting the 'mcp-seedream' package or the API domain, provide the package URL or token policy and I can help review further.

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-turbo offers 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_url and mask_url