Raindance AI — Put your cast in the scene
Raindance AI turns two character photos into a waterfront performance guided by a motion template. Choose your cast, check the estimate and generate your video here.
- Two character photos
- Motion template included
- Four model choices
- Video + audio references
Make your Raindance AI video
Two sample characters, the original Raindance outline motion reference and an audio reference are ready. Replace the portraits or try the preset, review the estimate, then generate.
dreamina-seedance-2-513-second preset · $3.7939
Start with two portraits, the outline motion template and an audio reference. Sound is generated with your video.
The shot: subject, action, camera move, lighting and style.
Use images as references, as the first frame, or as the first and last frames.
Files are uploaded and sent as URLs.
One character per slot, with face and outfit visible. Roles follow the performance across camera cuts.
Files are uploaded and sent as URLs.
One character per slot, with face and outfit visible. Roles follow the performance across camera cuts.
Files are uploaded and sent as URLs.
Supporting views follow the two main cast images.
Files are uploaded and sent as URLs.
The original outline is preloaded as @Video 1 to guide the shot sequence, movement and timing. Its duration contributes to the estimate.
Files are uploaded and sent as URLs.
@Audio 1 guides vocals and musical timing. Preview the result to check how the sound aligns with the performance.
Output resolution. 720p is the default.
Default is adaptive: the frame follows your prompt or input.
A fixed length, or auto to let the model choose.
The preset is 13 seconds; available lengths follow your chosen model.
On by default so the model generates sound with the performance. Audio reference guides the result; exact recording and lip sync are not guaranteed.
Add a watermark to the video. Off by default.
Also return the final frame as an image, for chaining shots.
mp4 or mov.
What to do with a reference video: reference it, edit it or extend it. Auto decides for you.
Seconds before an unfinished task expires, 3600–259200. Default 172800.
Whole number, 0–9.
An ID for your end user, up to 64 characters. A hash is fine.
On by default. Turning it off is available through the API only.
Greyed-out options relax content filtering. They are available through the API only, not in the playground.
Includes output and reference-video seconds. The final charge follows the completed generation.
Watch the Raindance trend reference
See the waterfront performance, character changes and soundtrack before choosing your own cast.
Your version starts with two photos
Keep the seated and singing roles, then replace the cast with your own two character images.
This clip demonstrates the trend. Generation uses the original outline motion template shown below, with audio supplied separately.
Two photos, one Raindance AI performance
Compare the source portraits with the generated clip. Watch both roles through the camera cuts, especially the faces, hands and clothing.
Preview the Raindance AI motion template
The original 13.13-second outline clip guides the motion and camera cuts. Your photos define the cast, and audio is supplied separately.
Cast by role, not by screen position
@Image 1 takes the seated role; @Image 2 takes the singing role. @Video 1 guides the shots, gestures and performance timing.
@Audio 1 provides a separate soundtrack reference. Keep generated audio on and review the timing and mouth movements in the finished result.
Choose your Raindance AI cast
A duo of your own
Build a Raindance AI scene around two distinct characters. Clear portraits and different outfits help you check which character stays in each role.
Original illustrated characters
Try two original illustrated characters with similar styles, then describe that style in the prompt.
A repeatable cast test
Keep the Raindance AI motion reference while changing one portrait. Compare results before changing other settings.
Starting ideas, not guaranteed results. Use images you have permission to use.
Raindance AI pricing
Raindance AI uses your SeedRouter balance and the selected model's current rate. The estimate includes reference-video time as well as output time.
Estimated / video
- Seedance 2.5
- $3.7939
- Seedance 2.0
- $2.552
- Seedance 2.0 Fast
- $1.9559
- Seedance 2.0 Mini
- $1.3288
Current Seedance rates
Compare the reference-video rows at the same resolution and duration.
| Category | dreamina-seedance-2-5 | dreamina-seedance-2-0 | dreamina-seedance-2-0-fast | dreamina-seedance-2-0-mini |
|---|---|---|---|---|
| 480P & reference video | $0.0646Price · 1 second | $0.0454Price · 1 second | $0.0348Price · 1 second | $0.0236Price · 1 second |
| 480P | $0.1080Price · 1 second | $0.0739Price · 1 second | $0.0591Price · 1 second | $0.0394Price · 1 second |
| 720P & reference video | $0.1452Price · 1 second | $0.0977Price · 1 second | $0.0748Price · 1 second | $0.0508Price · 1 second |
| 720P | $0.2428Price · 1 second | $0.1590Price · 1 second | $0.1271Price · 1 second | $0.0848Price · 1 second |
| 1080P & reference video | $0.3576Price · 1 second | $0.2400Price · 1 second | — | — |
| 1080P | $0.5971Price · 1 second | $0.3929Price · 1 second | — | — |
| 4K & reference video | — | $0.4918Price · 1 second | — | — |
| 4K | — | $0.8169Price · 1 second | — | — |
What is Raindance AI?
Raindance AI is a character-recasting video workflow built around the waterfront performance associated with Dave and Tems' Raindance. Two character images set the cast, while a short motion reference guides the gestures and camera cuts.
The Raindance AI Playground combines cast slots, video and audio references, and an editable prompt. Generate your performance with sound, preview the result and download the video.
Two ways to create Raindance AI
Generate on this page
Choose the cast, preview the reference and check the cost. Watch task progress and download the completed Raindance AI video here.
Build with the model API
Inspect your settings in the JSON view. Seedance documentation covers references, submission and result retrieval for your own application.
Shape your Raindance AI performance
Keep the roles clear
Separate cast slots put the seated character first and the singing character second. The prompt asks Raindance AI to keep each character's appearance consistent across the cuts.
Start with visible movement
Watch the supplied Raindance AI reference before generating. Keep its gestures and camera sequence, then change the cast without describing every movement from scratch.
Guide sound and performance together
The audio reference guides vocals and rhythm while the outline video guides the performance. Download the model’s audiovisual result directly and check the timing and lip sync before sharing.
How to make a Raindance AI video
- 01
Pick two character images
Replace the samples with one clear image per role. Keep the seated performer in Image 1 and the singing performer in Image 2.
- 02
Review the Raindance AI preset
Preview the outline motion template and audio reference, then read the prompt. Retain the role assignments when adjusting appearance instructions.
- 03
Check the estimate and generate
Choose a Seedance model and review its live estimate. Sign in, make sure your balance covers the task, then start generation.
- 04
Review the picture and sound
Watch the full Raindance AI clip. Compare the cuts and gestures with the reference, then listen while checking the singing character’s mouth movements. Download once you are happy with the result.
Raindance AI or the general Playground?
Start here for this performance. Use a model page to build a different scene from your own references.
| Starting point | Raindance AI | Seedance model page |
|---|---|---|
| Character inputs | Seated and singing role slots | General frame and reference inputs |
| Prompt | Raindance performance preset | General example prompt |
| Motion | Included outline reference | Supply your own reference |
| Sound | Audio reference; sound on | Model audio controls |
| Billing | Selected model's live rate | Same model's live rate |
Before you generate Raindance AI
Check likeness across every cut
Exact movement, identity and lip sync can vary. Inspect the full Raindance AI result before paying for another attempt.
Match your video and music
The outline motion template and soundtrack are separate references. Compare the finished video with both; exact vocals, cut timing and lip sync can vary.
Create Raindance AI on SeedRouter
One balance, four model choices
Compare supported Seedance models with the same cast and reference. Review the updated estimate before each Raindance AI attempt.
Pay as you create
Top up your balance when needed; unused credit does not expire. Raindance AI uses the same balance as other SeedRouter models. Failed requests are not charged.
Explore the Seedance models
Check each model's supported settings, live prices and API documentation.
Raindance AI guides
Follow the workflow, copy the prompt and troubleshoot character drift before another generation.
Raindance AI questions
Is Raindance AI free?+
Previewing the template does not start a paid task. Generation uses your SeedRouter balance at the chosen model's rate, shown before submission. There is no separate Raindance AI subscription.
Which photos should I use for Raindance AI?+
Use one clear character per slot, with face and outfit visible. Similar visual styles help describe the scene. Images remain subject to model checks; acceptance and exact likeness are not guaranteed.
Where is the Raindance AI prompt?+
The prompt is prefilled and editable in the Playground. It assigns the seated and singing roles and follows the motion reference's shot sequence. Reset restores the scene prompt, sample inputs and starting settings.
Does Raindance AI generate sound and lip sync?+
The preset includes an outline video and a separate audio reference, with generated audio enabled. The prompt asks the singing performer to follow the vocals. The model generates picture and sound together; exact lyrics, musical timing and lip sync still need review.
Can I change the Raindance AI model or format?+
Yes. Choose Seedance 2.5, 2.0, Fast or Mini. The preset is 13 seconds at 720p in 16:9; available settings and the estimate follow your selected model.
Why does my Raindance AI result look different?+
Images guide appearance; the reference guides performance. Conflicting styles, obscured faces or complicated instructions can confuse the result. Simplify one input at a time and compare both characters throughout the clip.
Make the Raindance AI scene your own
Choose two character images, preview the movement and check the estimate. Your Raindance AI performance starts with the cast you pick.