seedancetwo2.0

Seedance Two accepts four modality inputs — image, video, audio, and text — for richer expression and more controllable generation.

Reference Image to Video Precisely reproduce composition, character details, and visual style from a reference image to generate video.

Reference Video to Video Replicate camera movements, complex motion rhythms, and creative effects from a reference video to generate new video content.

Video Extension Smoothly extend and connect shots — generate continuous scenes guided by your prompts. Not just generation, but "keep shooting."

Video Editing Swap characters, remove or add elements in existing videos with targeted edits.

How to Use

1. Register / Log In

Click Sign In in the top-right corner to register or log in.

Social account login is supported.

2. Purchase Credits

Visit the /pricing page to choose a plan and recharge.

Annual subscription saves up to 89%.

Credits are used to generate videos.

3. Generate Videos (Core Feature)

The video generator is located at the bottom of the homepage and supports multiple creation modes:

Mode Description Text to Video Enter a text description and the AI automatically generates a video. Image to Video Upload an image as the starting frame for video generation. Reference Video Upload a reference video to replicate its camera movements, actions, and effects. Video Extension Extend an existing video by continuing the scene seamlessly. Video Editing Make targeted edits to existing videos (swap characters, add/remove elements).

Supports multiple output aspect ratios, including landscape, portrait, and square formats.

4. View Your Creations

Showcases Page: Browse featured examples and high-quality results.

Activity Page (after login): View your personal generation history.

5. Detailed User Manual

Visit /manual for the complete illustrated and video-based operation guide (Feishu-style layout).

6. Additional Features

Switch language (multi-language support) and dark/light theme in the top-right corner.

Contact support: support@seedancetwo.com

Visit /blog for product updates and usage tips.

Key Features

• Overall Consistency Significantly Improved。Character faces, clothing, fonts, and other details remain highly consistent across multiple shots, with no unexpected changes.
• Precise Camera Movement and Motion Replication。Upload a reference video to replicate complex character blocking and camera movements — no need for frame-by-frame descriptions.
• Creative Templates / Effect Replication。Accurately reproduce complex effects such as creative transitions, commercial-style edits, and cinematic scenes.
• Creative and Story Completion：The model intelligently completes story progression and creative details for more natural storytelling.
• Video Extension：Seamlessly extend and connect scenes — generate continuous shots based on prompts, not just create, but keep filming.
• More Accurate Voice, More Realistic Sound：More natural and realistic voice tones, with significantly improved lip-sync and narration performance.
• Smoother Long Takes：Long shots remain uninterrupted, with natural scene transitions and greatly improved shot continuity.
• Highly Practical Video Editing：Make targeted edits to specific segments of existing videos without regenerating the entire clip.
• Beat-Synced Music：Audio rhythm aligns precisely with on-screen actions, making videos more dynamic and rhythmic.
• Improved Emotional Expression：More accurate facial expressions and body language, resulting in stronger emotional impact and storytelling.

Use Cases

• The character in the painting shows a guilty expression, glancing left and right nervously. He leans out of the frame, quickly stretches his hand out of the canvas, grabs a can of cola, and takes a sip. A satisfied smile spreads across his face. Suddenly, the sound of approaching footsteps is heard. The character hurriedly puts the cola back in its original place. At this moment, a Western cowboy appears, picks up the cola from the cup, and walks away. Finally, the camera slowly pushes forward. The scene gradually fades into a pure black background, with only a can of cola illuminated by a top light. At the bottom of the screen, an artistic subtitle appears along with a voice-over: "Yikou Cola — A Taste You Can’t Miss!""https://image.agent-skills.cc/uploads/manual/v2_002.mp4
• he camera follows a man dressed in black as he runs frantically, chased by a group of people behind him. The angle shifts to a side-tracking shot. In panic, he crashes into a roadside fruit stand, gets up quickly, and continues running. Chaotic crowd noises fill the air.https://image.agent-skills.cc/uploads/manual/v2_004.mp4
• Use the actress in @Image1 as the main subject, and reference the camera movement style from @Video1, incorporating rhythmic push, pull, pan, and tracking movements.https://image.agent-skills.cc/uploads/manual/v2_020.mp4。https://image.agent-skills.cc/uploads/manual/v2_021.mp4