Special Techniques Collection

Table of Contents

• Special Technique: Text Generation
• Special Technique: Video Extension vs Segmented Stitching
• Special Technique: Material Configuration Strategy

---

Special Technique: Text Generation

Overview

Seedance 2.0 series models support generating common text. The model automatically matches an appropriate style and color based on the context, and also supports specifying text color, style, appearance method, appearance timing, and appearance position in the prompt.

Writing Principles

Prioritize commonly used characters, avoiding rare characters and special symbols to ensure the best presentation quality.

Three Text Scenarios

1. Slogan

Template:

"Text content" + "Appearance timing" + "Appearance position" + "Appearance method", "Text features (color, style)"

Example:

Hand-drawn comic style, three people sitting together eating the fried chicken from image 1, with a friendly and pleasant atmosphere. The scene gradually blurs, and text appears in the center of the frame: "Happiness is in Seedance".

Result:

2. Subtitles

Template:

Subtitles appear at the bottom of the frame with the content "……". The subtitles must be fully synchronized with the audio rhythm.

Example:

Generate a video with voiceover. A deep, calm male voice says: "In the vast universe, our world is but a fleeting moment. Yet within it, life flourishes against all odds." The scene should transition slowly from night to dawn, with stars gradually disappearing and the sun rising behind the mountains. Subtitles matching the spoken lines appear at the bottom of the frame.

Result:

3. Speech Bubbles

Template:

"Character" says: "……", with speech bubbles appearing around the character as they speak, containing the spoken lines.

Example:

The two people in the image are chatting in the office. The woman speaks first, saying: "You arrive right on time every time — do you enjoy that just-in-time feeling?" The man smiles and replies: "I have my own rhythm." The dialogue is casual and natural as the characters speak, with matching subtitles appearing at the bottom of the frame.

---

Special Technique: Video Extension vs Segmented Stitching

Comparison of the Two Approaches

Feature	Video Extension	Segmented Stitching
Suitable Scenarios	"Dialogue scenes" within a single setting	Plot twists or complex "action scenes"
Typical Uses	Long conversations, emotional buildup, single-path movement	Chases, fights, montage
Effect	Immersive, coherent one-take sequence	Fast-paced, strong visual impact
Implementation	Model-native extension function	Generate segments independently, then edit and assemble

Practical Production Strategy

Typically, both methods are used together:

• First, use Video Extension to generate coherent dialogue segments
• Then, stitch in atmospheric shots or transition clips
• Balancing immersion with rhythmic variation

---

Special Technique: Material Configuration Strategy

Four Functional Roles

Materials are typically divided into four "functional roles":

Role	Function	Recommended Form
Character Anchor	Lock in character appearance	Portrait / full-body shot
Scene Setting	Lock in environment and style	Scene photo / concept art
Camera Reference	Lock in camera language and action rhythm	Reference video
Rhythm & Atmosphere	Use audio to control mood and timbre	Ambient sound / background music

Recommended Configuration

4-5 materials in total

• 1-2 character images (facial close-up + full body)
• 1 scene image
• 1 camera reference video
• 1 audio clip

Notes

• Avoid using the maximum material limit
• Too many materials make it difficult for the model to prioritize feature importance
• Prone to style conflicts, blurred subject identification, and results deviating from expectations