seedream

Generate AI images from prompts with optional reference images.

5.8k|918|Updated Feb 12, 2026
One-click install
npx skills add https://github.com/netease-youdao/LobsterAI --skill seedream
Or copy as Structured Prompt for Agent
Please help me install this Agent Skill.
Skill: seedream
Source: https://github.com/netease-youdao/LobsterAI/tree/main/SKILLs/seedream
Command: npx skills add https://github.com/netease-youdao/LobsterAI --skill seedream

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes scripts (resource) components.

What problem does it solve?

Seedream enables quick generation of high-quality AI images from prompts, with options for editing, fusion of multiple references, montage-style outputs, and even real-time inspiration from web search when available.

Core Features & Use Cases

  • Text-to-image (T2I): generate images from descriptive prompts.
  • Image-to-image (I2I): edit existing images using text prompts.
  • Multi-image fusion: blend features from several reference images.
  • Montage / group image generation: create sequences or themed image sets.
  • Online search integration: fetch current references to guide visuals.

Quick Start

Provide a prompt and optional reference images to Seedream to generate one or more AI images.

Frequently Asked Questions about seedream

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I generate AI images from text prompts with reference images?

To generate AI images from text prompts with reference images, provide a descriptive prompt and optional seed references to Seedream. It supports text-to-image, image-to-image, and multi-image fusion workflows.

Can I blend features from multiple images into one AI generated picture?

Yes, you can blend features from multiple images into one AI generated picture using the multi-image fusion feature. Seedream analyzes the provided reference images and merges their visual characteristics based on your prompt.

How does online search integration work for AI image generation?

Online search integration fetches current visual references from the web to guide AI image generation. Seedream uses these real-time search results to inspire and direct the visual output of your text prompts.

Do I need an API key to start generating text-to-image art?

Yes, you need an API key configured to start generating text-to-image art. The Seedream workflow strictly enforces API key configuration and model selection before processing any image generation requests.

What is the best way to edit an existing image using an AI prompt?

The best way to edit an existing image using an AI prompt is the image-to-image feature. Seedream takes your original image and applies text prompt instructions to modify and recreate the visual content accurately.

Are there limitations when creating montage-style image sequences?

When creating montage-style image sequences, limitations include model selection constraints and strict size settings. Seedream handles error and status checking during montage generation to ensure reliable production outputs.