Seedream AIGC

A powerful Dify plugin providing comprehensive AI-powered image and video generation capabilities using Volcengine Doubao's latest Seedream and Seedance models. Supports text-to-image, text-to-video, image-to-image, image-to-video, multi-image fusion, and more with professional-grade quality and flexible configuration options.

Version Information

• Current Version: v0.0.2
• Release Date: 2026-02-13
• Compatibility: Dify Plugin Framework
• Python Version: 3.12

Version History

• v0.0.2 (2026-04-16): Added Seedance 2.0 model support, video download feature, and icon configuration fixes
• v0.0.1 (2026-02-13): Initial release with image and video generation capabilities

Quick Start

1. Install the plugin in your Dify environment
2. Configure your Volcengine API credentials (API Key)
3. Start generating images and videos with AI

Key Features

• Multiple Generation Modes: Text-to-image, text-to-video, image-to-image, image-to-video, multi-image fusion
• Latest AI Models: Supports Seedream 4.0, 4.5, 5.0 Lite for images; Seedance 1.0 Pro, 1.0 Pro Fast, 1.5 Pro, 2.0 for videos
• Flexible Image Sizes: Multiple aspect ratios from 1:1 to 21:9 with resolutions up to 3024x1296
• Video Generation: Create videos up to 12 seconds with synchronized audio (Seedance 1.5 Pro)
• Multi-Image Support: Generate images from multiple reference images (2-14 images)
• First-Last Frame Video: Create videos from first and last frame images
• Batch Generation: Generate multiple images in a single request
• Draft Mode: Quick preview generation for faster iteration
• Watermark Control: Optional AI-generated watermark for content authenticity

Core Features

Image Generation

Text to Image (text_2_image)

Generate images from text descriptions using Seedream models.

• Supported Models: Seedream 4.0, Seedream 4.5, Seedream 5.0 Lite
• Features:
  • Multiple aspect ratios (1:1, 4:3, 3:4, 16:9, 9:16, 3:2, 2:3, 21:9)
  • High resolution up to 3024x1296
  • Optional watermark
  • Fast generation speed

Image to Image (image_2_image)

Generate images from text and a reference image.

• Supported Models: Seedream 4.0, Seedream 4.5, Seedream 5.0 Lite
• Features:
  • Reference image guided generation
  • Multiple aspect ratios
  • Optional watermark
  • Support for jpeg, png, webp, bmp, tiff, gif formats (max 10MB)

Multi-Image Fusion (multi_images_2_image)

Generate an image from text and multiple reference images (2-14 images).

• Supported Models: Seedream 4.0, Seedream 4.5, Seedream 5.0 Lite
• Features:
  • Combine up to 14 reference images
  • Intelligent image fusion
  • Multiple aspect ratios
  • Optional watermark

Multi-Image Group (multi_images_2_multi_images)

Generate a group of images from text and multiple reference images.

• Supported Models: Seedream 4.0, Seedream 4.5, Seedream 5.0 Lite
• Features:
  • Generate 1-15 images per request
  • Multiple reference images support (2-14)
  • Batch generation
  • Multiple aspect ratios

Video Generation

Text to Video (text_2_video)

Generate videos from text descriptions using Seedance models.

• Supported Models: Seedance 1.0 Pro, Seedance 1.0 Pro Fast, Seedance 1.5 Pro, Seedance 2.0, Seedance 2.0 Fast
• Features:
  • Duration: 2-15 seconds (Seedance 2.0/2.0 Fast supports 4-15)
  • Resolution: 480p, 720p, 1080p
  • Aspect ratios: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, adaptive
  • Synchronized audio generation (Seedance 1.5 Pro / 2.0 / 2.0 Fast)
  • Draft mode for quick preview
  • Fixed camera option (not available for Seedance 2.0/2.0 Fast)
  • Service tier selection (Seedance 2.0/2.0 Fast use default only)

Image to Video (image_2_video)

Generate video from a single image with text description.

• Supported Models: Seedance 1.0 Pro, Seedance 1.0 Pro Fast, Seedance 1.5 Pro, Seedance 2.0, Seedance 2.0 Fast
• Features:
  • Single image input
  • Duration: 2-15 seconds (Seedance 2.0/2.0 Fast supports 4-15)
  • Resolution: 480p, 720p, 1080p
  • Adaptive aspect ratio support
  • Synchronized audio generation
  • Draft mode available

First-Last Frame Video (images_2_video)

Generate video from first and last frame images.

• Supported Models: Seedance 1.0 Pro, Seedance 1.5 Pro, Seedance 2.0, Seedance 2.0 Fast
• Features:
  • First and last frame input
  • Smooth transition generation
  • Duration: 2-15 seconds (Seedance 2.0/2.0 Fast supports 4-15)
  • Resolution: 480p, 720p, 1080p
  • Synchronized audio generation
  • Draft mode available

Video Query (video_query)

Query the status and results of video generation tasks.

• Features:
  • Real-time task status
  • Video download URL retrieval
  • Last frame image return option

Technical Advantages

• Latest AI Models: Access to Doubao's newest Seedream and Seedance models
• High Quality Output: Professional-grade image and video generation
• Flexible Configuration: Extensive parameter options for fine-tuning
• Async Processing: Efficient video generation with task-based workflow
• Multi-Format Support: Support for various image and video formats
• Audio Generation: Automatic synchronized audio for videos
• Batch Processing: Generate multiple images efficiently
• Draft Mode: Quick preview for faster iteration cycles

Requirements

• Python 3.12
• Dify Platform access
• Volcengine API credentials (API Key)
• Required Python packages (installed via requirements.txt):
  • dify_plugin>=0.2.0
  • requests>=2.31.0,<3.0.0
  • pillow>=10.0.0,<11.0.0

Installation & Configuration

1. Install the required dependencies:

2. Configure your Volcengine API credentials in the plugin settings:

   • API Key: Your Volcengine API key

3. Install the plugin in your Dify environment

Usage

Image Generation Tools

1. Text to Image

Generate images from text descriptions.

• Parameters:
  • : Text description of the image (required)
  • : Image size (default: 2048x2048)
  • : Enable/disable watermark (default: true)
  • : Model version (default: Seedream 4.5)

2. Image to Image

Generate images from text and a reference image.

• Parameters:
  • : Text description (required)
  • : Reference image file (required)
  • : Image size (default: 2048x2048)
  • : Enable/disable watermark (default: true)
  • : Model version (default: Seedream 4.5)

3. Multi-Image Fusion

Generate an image from multiple reference images.

• Parameters:
  • : Text description (required)
  • : Reference images (2-14 images, required)
  • : Image size (default: 2048x2048)
  • : Enable/disable watermark (default: true)
  • : Model version (default: Seedream 4.5)

4. Multi-Image Group

Generate multiple images from reference images.

• Parameters:
  • : Text description (required)
  • : Reference images (2-14 images, required)
  • : Maximum images to generate (1-15, default: 3)
  • : Image size (default: 2048x2048)
  • : Enable/disable watermark (default: true)
  • : Model version (default: Seedream 4.5)

Video Generation Tools

5. Text to Video

Generate videos from text descriptions.

• Parameters:
  • : Text description (max 500 chars, required)
  • : Model version (default: Seedance 1.5 Pro)
  • : Video resolution (default: 720p)
  • : Aspect ratio (default: 16:9)
  • : Duration in seconds (2-15, default: 5)
  • : Random seed (-1 for random)
  • : Fixed camera position
  • : Enable/disable watermark
  • : Generate synchronized audio
  • : Draft mode for quick preview
  • : Return last frame image in query
  • : Service tier (default/flex)

6. Image to Video

Generate video from a single image.

• Parameters:
  • : Text description (required)
  • : Input image (required)
  • Other parameters same as Text to Video

7. First-Last Frame Video

Generate video from first and last frame images.

• Parameters:
  • : Text description (required)
  • : First frame image (required)
  • : Last frame image (required)
  • Other parameters same as Text to Video

8. Video Query

Query video generation task status.

• Parameters:
  • : Video generation task ID (required)
  • : Download video file when available (default: true)

Supported Image Sizes

Notes

• Video generation is asynchronous; use Video Query to check status and retrieve results
• Seedance 1.5 Pro, 2.0, and 2.0 Fast support synchronized audio generation
• Draft mode provides faster generation for quick previews
• Flex service tier offers cost-effective processing with longer wait times
• Maximum prompt length for video generation is 500 characters
• Reference images should be under 10MB in size
• Multi-image fusion supports 2-14 reference images

Developer Information

• Author:
• Email: [email protected]
• License: Apache License 2.0
• Source Code:
• Support: Through Dify platform and GitHub Issues

License Notice

This project is licensed under Apache License 2.0. See LICENSE [blocked] file for full license text.

---

Ready to create stunning images and videos with AI?