dola-seedream#

Description#

Generate high-quality images from text prompts using BytePlus Seedream models. This skill provides access to three powerful Seedream model versions (4.0, 4.5, and 5.0), each offering unique capabilities for different use cases.

When to Use This Skill#

Use this skill when:

• Users want to create images from text descriptions
• Users need to generate artwork in various artistic styles
• Users want to create visual content for creative projects
• Users need AI-powered image generation capabilities
• Users want to convert reference images to different styles
• Users need to generate multiple images in batch
• Users require high-quality, professional-looking images

Model Versions#

VersionModel NameRelease DateRecommendationBest For4.0seedream-4-0-250828August 2025⭐⭐⭐Daily use, supports 1K/2K/4K and Fast mode4.5seedream-4-5-251128November 2025⭐⭐⭐⭐Detail-oriented, supports 2K/4K5.0-liteseedream-5-0-2601282026⭐⭐⭐⭐⭐Highest quality, supports 2K/3K and PNG output

Features#

• Text-to-Image: Generate images from detailed text descriptions
• Image-to-Image: Transform reference images (up to 14) into new creations
• Batch Generation: Create multiple related images in a single request (up to 15)
• Flexible Resolution: Support for resolution presets (1K, 2K, 3K, 4K) or custom sizes
• Multiple Versions: Choose from 4.0, 4.5, or 5.0-lite models
• Watermark Control: Option to disable watermarks
• Output Formats: PNG and JPEG formats (5.0-lite only)
• Prompt Optimization: Choose between standard and fast (for 4.0) modes

Installation & Setup#

Prerequisites#

bash

# Required: API Key configuration (Get from BytePlus Console)
export ARK_DOLA_API_KEY="your-api-key-here"

Usage#

Command Line#

bash

python scripts/seedream_image_generate.py -p "A cute kitten playing in a garden" --version 5.0

Command Line Options#

OptionShortcutDescriptionDefault--prompt``-pImage description text (required)---version``-vVersion selection: 4.0, 4.5, 5.0-lite``5.0-lite``--size``-sImage dimensions (1K/2K/3K/4K or WxH)2K``--image``-iSingle reference image URL---images-Multiple reference image URLs (space separated)---group``-gEnable batch image generationfalse``--max-images-Maximum images for batch generation15``--output-format-Output format: png or jpeg (5.0-lite only)jpeg``--response-format-Response format: url or b64_json``url``--prompt-mode-Prompt optimization mode: standard or fast``standard``--timeout``-tTimeout in seconds1200``--no-watermark-Disable watermarkfalse``--stream-Enable server-side streamingfalse

Python API Usage#

python

import asyncio
from scripts.seedream_image_generate import seedream_generate

async def main():
    # Generate image using 5.0 version
    result = await seedream_generate([
        {
            "prompt": "A futuristic city landscape",
            "size": "2048x2048",
            "output_format": "png"
        }
    ], version="5.0")

    print(result)

if __name__ == "__main__":
    asyncio.run(main())

Version Selection Guide#

Choose 4.0 if:#

• You need quick daily generation
• Quality requirements are not extremely high
• You need faster generation speed
• Simple scenes and styles

Choose 4.5 if:#

• You want richer details
• You're working with complex scenes
• You need better style reproduction
• You have moderate quality requirements

Choose 5.0 (Recommended) if:#

• You want the highest quality
• You need breakthrough creative expression
• You have extreme detail requirements
• You need tools parameter (like web search) ⭐
• You need custom output format (png/jpeg) ⭐
• Important projects and work

When in doubt, use 5.0! ⭐

Prompt Engineering Tips#

Basic Prompt Structure#

text

[Subject Description] + [Style/Art Movement] + [Lighting/Atmosphere] + [Quality/Resolution]

Advanced Prompts (Optimized for 5.0)#

text

[Subject Description], [Creative Style/Art Movement], [Unique Perspective/Composition], [Special Lighting/Atmosphere], [Emphasizing 5.0 creative expression]

Parameter Support by Version#

ParameterSeedream 4.0Seedream 4.5Seedream 5.0Descriptionmodel✅✅✅Model nameprompt✅✅✅Prompt (required)image✅✅✅Reference image(s)size✅✅✅Image dimensionssequential_image_generation✅✅✅Batch generation controlsequential_image_generation_options✅✅✅Batch generation configresponse_format✅✅✅Response format (url/b64_json)watermark✅✅✅Watermark (true/false)stream✅✅✅Streaming outputoptimize_prompt_options✅✅✅Prompt optimization configtools❌❌**✅Tool configuration (5.0 only)output_format❌❌✅**Output format (png/jpeg, 5.0 only)

FAQ#

Q: What's the difference between the versions?#

A: 4.0 is for quick daily use, 4.5 offers better details for complex scenes, and 5.0 provides the highest quality with unique tools support.

Q: How long are generated URLs valid?#

A: URLs are valid for 24 hours. Please download and save your images promptly.

Q: What image formats are supported for references?#

A: Common formats like JPG and PNG are supported, provided via URL or Base64.

Q: Can I use multiple versions in one call?#

A: Currently, only one version per call. For comparisons, make separate calls for different versions.

License#

This skill is licensed under the Apache License 2.0. See the LICENSE file for details.

Notice#

Please comply with BytePlus's terms of service and relevant laws and regulations when using this skill.