Model guide
Seedance 2.0 model guide
Seedance 2.0 is a flexible AI video model for controlled image-to-video, text-to-video, and multimodal reference workflows. Start with a product photo, portrait, illustration, campaign visual, or written scene, then direct subject motion, camera behavior, pacing, and output settings from one model workspace.
Read the Seedance image-to-video walkthroughWhat Seedance 2.0 is best for
It works well when speed, repeatable controls, and practical creative iteration matter. It is designed for teams that need several aspect ratios, selectable duration and resolution, frame-guided generation, or multiple creative variations before choosing a final video direction.
Seedance 2.0 vs Veo 3.1
Seedance 2.0 is the better fit when you want controlled image-to-video iteration, explicit production settings, and faster testing across formats. Veo 3.1 is better when the project depends more on cinematic camera language and atmosphere.
Explore the Veo 3.1 video generatorGeneration modes
The generator separates four workflows so each input has a clear role. Choose text-to-video when the scene begins with a prompt, reference mode for multimodal guidance, first-frame mode to animate one opening image, or first-and-last-frame mode to guide both ends of the shot.
Text to video
Describe the subject, environment, action, camera movement, lighting, and mood without uploading media. Text-to-video is useful for concept exploration, establishing shots, visual storyboards, and ideas that do not need to preserve an existing product or character image.
Multimodal reference to video
Guide Seedance 2.0 with reference images, short video clips, and audio files in the same request. This mode is designed for creative direction that depends on visual identity, movement examples, rhythm, or sound, rather than treating a single image as the exact opening frame.
First-frame image to video
Upload one image as the opening frame and describe what should happen next. The model uses that frame as the starting composition, making this mode suitable for animating a product photo, portrait, illustration, landscape, or designed campaign visual.
First and last frame to video
Provide an opening image and an ending image to define the visual transition. The prompt should explain the motion between them, helping the model create a shot with a clearer destination than a first-frame-only generation.
Typical workflow
The Seedance 2.0 workflow is built for repeatable image-to-video generation: start from a reference, define motion, choose production settings, then iterate.
- 1Upload or choose a reference image to anchor the visual style.
- 2Write a motion prompt describing camera movement, subject action, mood, and pacing.
- 3Select the speed, duration, resolution, aspect ratio, and audio options.
- 4Generate a short video draft, review it, and reuse the prompt for the next variation.
How to write a Seedance 2.0 prompt
A useful prompt describes visible change instead of relying on broad adjectives. Write the shot in a logical order: identify the subject, specify its action, define camera movement, describe the environment and lighting, then state the pacing or final composition you want.
Anchor the subject
Name the main subject and the details that must remain recognizable, such as product shape, clothing, facial direction, logo placement, or illustration style. Clear visual anchors reduce ambiguity when the model adds motion to a still image.
Separate subject and camera motion
Explain what the subject does and how the camera responds. For example, describe a bottle rotating slowly while the camera pushes in, or a person turning toward the light while the shot tracks from left to right.
Control pacing and continuity
Use timing words such as slowly, steadily, in one continuous take, or with a gentle finish. When using first and last frames, describe the transition between them so the model understands the intended path instead of inventing unrelated changes.
Write for the destination format
Mention whether the result is a vertical social ad, a widescreen product reveal, a quiet brand loop, or a fast concept draft. The intended use helps align framing, movement intensity, empty space, and overall visual rhythm.
Choosing the right settings
This workspace offers Standard and Fast variants, durations from 4 to 15 seconds, multiple landscape, square, and portrait aspect ratios, and resolution choices that depend on the selected variant. Use Fast for lower-cost exploration and repeated prompt tests; use Standard when the chosen resolution and final visual quality matter more. Longer clips give an action more time to develop, while shorter clips usually produce a tighter and easier-to-control movement. Optional audio and web-assisted text generation should only be enabled when they support the actual creative brief.
See credit pricingUse cases
Seedance 2.0 is a strong fit when a team needs fast image-to-video output with enough control to match different channels and formats.
For commerce teams
Product videos for e-commerce pages, launch teasers, and paid social ads.
For creators and agencies
Portrait, lifestyle, and UGC-style clips that need natural subject motion.
For creative testing
Rapid creative testing when a team needs several image-to-video directions.
Frequently asked questions
These answers cover the common Seedance 2.0 image-to-video questions users check before creating a video draft.
Is Seedance 2.0 for image-to-video generation?
Yes. This workspace is focused on image-to-video generation, where the source image provides the visual reference and the prompt controls motion.
Which Seedance 2.0 settings can I control?
You can control speed mode, duration, resolution, aspect ratio, and whether audio should be generated when the selected model supports it.
When should I choose Seedance 2.0 instead of Veo 3.1?
Choose Seedance 2.0 when you want faster image-to-video iteration with explicit production settings. Choose Veo 3.1 when the priority is a more cinematic motion direction.