Seedream Quick Start Guide

Welcome to the Seedream Quick Start Guide! Seedream (Jimeng AI) is ByteDance's AI creation platform supporting image generation, smart editing, and video generation. This tutorial will help you master the core features from scratch.

Introduction to Seedream

Seedream (Jimeng AI) is an AI creative tool developed by ByteDance based on the Skylark model, currently offering versions 3.0, 4.0, and 4.5. Compared to other AI art tools, Seedream has unique advantages in Chinese language understanding, Eastern aesthetics, and traditional Chinese art creation.

Main Function Modules

• Image Generation: Text-to-image, image-to-image, smart reference
• Smart Canvas: Inpainting, outpainting, erase, upscale
• Video Generation: Image to video, text to video
• Story Creation: Storyboard generation, character consistency

Registration and Login

Access Seedream

1. Open browser and visit jimeng.jianying.com
2. Click the "Start Jimeng" button to enter

Account Registration

Seedream currently only supports Douyin account login:

• Douyin Account: Open "Douyin APP" and scan the QR code in the top left corner to login

Interface Tour

After logging in, you'll see the Seedream main interface. Let's get familiar with the functional areas:

Main Area Descriptions

Area	Function
Left Navigation	Home, Generate, Assets, Canvas
Upper Creation Area	Prompt input, reference image upload
Lower Inspiration Area	Excellent works from other users for learning

Generate Your First Image

Step 1: Enter Prompt

In the input box at the center of the page, describe the scene you want to generate in Chinese or English:

Step 2: Select Model

Click the "Model" dropdown at the top and choose the appropriate version:

• Seedream 3.0: Fast speed, good for quick trials
• Seedream 4.0: High quality, rich details
• Seedream 4.5: Latest version, best results

Step 3: Set Aspect Ratio

Choose the appropriate ratio based on usage:

• 1:1: Avatars, memes
• 9:16: Phone wallpapers, short video covers
• 16:9: Desktop wallpapers, PPT images
• 3:4: Xiaohongshu, Instagram

Step 4: Generate Image

Click the "Generate Now" button, wait 10-30 seconds, and AI will generate 4 images for you to choose from.

Step 5: Download or Edit

Hover over your favorite image and click:

• 💾 Download: Save to local
• ✏️ Edit: Enter smart canvas to modify
• 🔄 Redraw: Regenerate based on current image
• ⭐ Save: Save to personal gallery

Prompt Structure Formula

Prompt Writing Tips

Chinese Prompt Advantages

Seedream understands Chinese very well. You can describe directly in natural language:

Prompt Structure Formula

Common Style Keywords

Style Type	Keywords
Chinese Traditional	Ink painting, Gongbi, Ancient style, Xianxia
Modern Style	Flat illustration, 3D render, Cyberpunk, Minimalist
Art Style	Oil painting, Watercolor, Sketch, Printmaking, Pop art
Photography	Portrait, Landscape, Macro, Long exposure

Image Editing Features

Click the "Edit" button on the generated image to enter the smart canvas:

Main Editing Functions

1. Inpainting

Use brush to paint the area you want to modify, then enter new description:

• Paint clothing → Enter "change to red dress"
• Paint background → Enter "change to starry sky background"

2. Outpainting

Expand image boundaries, AI automatically fills the scene:

• Click the outpainting button
• Select expansion direction (up/down/left/right)
• AI automatically fills the new area

3. Erase

Remove unwanted elements from the image:

• Paint the object to be removed
• Click the erase button
• AI intelligently repairs the background

4. Upscale

Increase image resolution:

• Supports 2x and 4x upscaling
• Maintains clarity
• Suitable for print output

Smart Canvas Usage

Smart Canvas is Seedream's core feature, supporting image editing and navigation:

Image Editing

• Inpainting: Fine-tune image elements
• Upscale: Supports 2x and 4x upscaling, maintains clarity, suitable for print output
• Cutout: Intelligently identifies and extracts people or objects
• Outpainting: Expand image boundaries, AI automatically fills the scene
• Video Generation: Convert static images to dynamic videos
• Eraser: Remove unwanted elements from the image
• Text Redraw: Modify text in the image

Reference Image Function

Upload reference images for AI to learn style or composition:

1. Click "Reference Image" button
2. Upload local image or select from history
3. Select reference type: Style / Composition / Character
4. Adjust reference strength (0-100%)

Video Generation

Seedream supports converting static images to dynamic videos:

Image to Video

1. Select a generated image
2. Click "Generate Video" button
3. Select motion intensity (Slight/Medium/Strong)
4. Click generate and wait 1-2 minutes

Video Parameter Settings

Parameter	Description
Duration	3 seconds, 5 seconds, 10 seconds
Frame Rate	24fps, 30fps
Resolution	720p, 1080p
Motion Intensity	Slight, Medium, Strong

Model Version Selection

Different Seedream model versions have different characteristics:

Version	Features	Use Cases
Seedream 3.0	Fast generation, fewer credits	Quick trials, sketch concepts
Seedream 4.0	Quality improvement, richer details	Daily creation, social media
Seedream 4.5	Latest version, best results	Professional creation, commercial use

Practical Tips Summary

1. Daily Free Credits

• New users get daily credits
• Different models consume different credits (3.0 < 4.0 < 4.5)
• Extra credits through check-in and sharing

2. Work Management

• All generated works auto-saved to "Works" page
• Support creating folders for organization
• Batch download or delete supported

3. Inspiration Community

• Browse other users' excellent works
• One-click copy others' prompts
• Follow favorite creators