Seedance 2.0 User Guide
A practical guide to the current text-to-video and image-to-video workflow.
Quick Start: The 3-Minute Video
Upload
Drag & drop your reference image (character/style) into the 'Image' tab.
Prompt
Describe the action simply: 'A cinematic shot of [reference] walking in rain.'
Generate
Hit generate. Wait ~60s. Preview results and download if satisfied.
The Core Workflow
The current generator is straightforward: either start from text, or upload one image and animate it with a prompt.
1. Asset Preparation
- Character Sheet: Use a clear, front-facing photo of your character. Avoid messy backgrounds.
- Style Reference: (Optional) An image defining the color palette or lighting.
2. Reference Image
For image-to-video, upload one clear starting image. Video reference and audio reference inputs are not exposed in the current UI.
Prompting Best Practices
Structure your prompts for maximum control.
"A cyberpunk samurai (@image1) unsheathing a katana slowly, low angle dolly zoom, neon rain, volumetric fog, 8k resolution."
Audio Option
The current generator exposes a basic audio toggle. Dedicated audio-reference, voice, and lip-sync workflows are not currently available in this UI.
Current
Use the built-in audio option when you want the generated clip to include ambient sound output.
Not Yet Exposed
Uploading voice, music, or reference audio is not part of the current product workflow.
Advanced: Achieving Consistency
With the current UI, consistency mainly comes from a clean starting image and a stable prompt structure.
Strategy 1: Start From One Strong Image
Use one clean, readable image as the base and avoid changing too many variables at once.
- • One clear product, character, or scene image
- • Reuse the same image when iterating on prompt variations
"A clean cinematic close-up of the same subject, slow camera push, soft rim light..."
Multi-Shot Consistency
To keep a character consistent across different scenes (e.g., Scene A: Living Room, Scene B: Park):
- Use the exact same @image reference for every generation.
- Keep the Subject Description in your prompt identical (e.g., "A young woman with red hair").
- Only change the Action and Environment words.
Shot Planning
Need better motion? Be explicit in the prompt about camera movement and speed.
Common Issues
Faces look distorted in motion
Use a higher resolution reference image. Try to avoid extreme close-ups combined with fast motion.
Text in video is garbled
AI struggles with specific text. Avoid prompts asking for signs/logos unless using post-production overlay.
Generation failed / Timeout
High demand on servers. Try again during off-peak hours or check your credit balance.