Special Topics Collection

---

Special Topics: Text Generation

Overview

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

Writing Principles

Prioritize commonly used characters and avoid rare characters and special symbols to ensure the best presentation.

Three Text Scenarios

1. Slogan

Template:

「Text content」+「Appearance timing」+「Appearance position」+「Appearance method」,「Text characteristics (color, style)」

Example:

Hand-drawn comic style, three people sitting together eating the fried chicken from picture 1, the atmosphere is friendly and pleasant, then the frame gradually blurs, and the text "Happiness lies in Seedance" appears in the center of the frame.

2. Subtitles

Template:

Subtitles appear at the bottom of the screen, the subtitle content is "……", 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 thrives against all odds." The scene should slowly transition from night to dawn, stars gradually disappearing, the sun rising from behind the mountains. Subtitles appear at the bottom of the screen in sync with the dialogue.

3. Speech Bubbles

Template:

「Character」says: "……", a bubble appears around the character when speaking, with the dialogue written inside the bubble.

Example:

The two people in the picture are chatting in the office. The woman speaks first and says: "You arrive just on time every time — do you enjoy that just-in-time feeling?" The man smiles and replies: "I have my own rhythm." When the characters speak, the conversation is casual and natural, with corresponding subtitles appearing at the bottom of the screen.

---

Special Topics: Video Extension vs. Segmented Splicing

Comparison of the Two Methods

Feature	Video Extension	Segmented Splicing
Applicable Scenarios	"Dialogue scenes" within a single scene	Plot twists or complex "action scenes"
Typical Uses	Long conversations, emotional progression, single-path movement	Chases, fights, montages
Effect	Immersive, continuous one-shot take	Fast-paced, strong visual impact
Implementation	Model-native extension function	Generate segments independently, then edit and combine

Practical Production Strategy

Typically, the two methods are used together:

• First, use Video Extension to generate coherent dialogue passages
• Then splice in cutaway shots or transition segments
• Balancing immersion with rhythmic variation

---

Special Topics: Material Configuration Strategy

Four Functional Roles

Materials are typically divided into four "functional roles":

Role	Function	Recommended Form
Character Anchoring	Lock in character appearance	Character close-up / 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 total

• Character images 1-2 (facial close-up + full body)
• Scene image 1
• Camera reference video 1
• Audio 1

Notes

• It is not recommended to use up the material limit
• Too many materials can make it difficult for the model to prioritize features
• Can lead to style conflicts, blurred subject recognition, and results deviating from expectations