Prompt-first creation
Start from a text description, then add supporting references only when the shot needs tighter control.
AI Video Generator
Create AI videos with Seedance
Use a focused generation workspace with a left-side control panel and a right-side conversation view for task progress and final videos.
Key points
1Main generation workspace
This is the central route for text-to-video and reference-driven creation.
MultiReference inputs
Prompts, images, video references, and audio context all feed the workflow.
LiveTask tracking
The app follows progress and exposes completed videos inside the same workspace.
Highlights
- Start from text prompts or uploaded references.
- Reference uploaded assets with @1, @2, @3 inside the prompt.
- See the active model reference limits directly in the prompt panel.
- Choose Seedance video models, ratio, resolution, and duration.
- Track generation progress in a conversation-style workspace.
- Review completed tasks from the account task page.
Public Sunday routes
HomeA focused Seedance 3.0 entry point for AI video creation.MembershipCompare Stars, subscriptions, one-time top-ups, and creator access.AI Video GeneratorCreate AI videos with prompts, reference uploads, model controls, and task progress.AI Video EnhancementImprove uploaded video resolution, frame rate, and bitrate with MediaKit.AI Image GeneratorPrepare AI image prompts, reference images, model choices, and image size controls.World Cup 2026Generate football-style AI clips from a portrait with player and stadium presets.HappyHorse 1.1Review the HappyHorse 1.1 landing page, benchmarks, and integrated workflow notes.Seedance 2.5Create 4-30 second multimodal videos with Seedance 2.5 at 480p, 720p, or 1080p.CommunityBrowse creator posts, published AI videos, and remixable generation notes.Help CenterRead workflow guidance, model notes, Star cost examples, and support information.AI BotRead API key, upload, task creation, and polling docs for bots, scripts, and agents.BlogRead the latest creator guides, product updates, and AI video insights.Commercial GuideRead commercial AI video guides, prompt examples, and ad workflow ideas.Privacy PolicyUnderstand how Seedance handles accounts, data, payments, and cookies.Terms of ServiceReview platform rules, acceptable use, membership terms, and open-source notices.
About this route
The video generator is the primary Sunday workspace for signed-in creators who want a direct path from prompt to task result.
The prompt panel lists the reference limits of the selected model: Seedance 2.5 accepts up to 30 images, 10 videos and 10 audio clips (each video or audio 2-30 seconds, 30 seconds in total), while Seedance Mini, Fast and High accept up to 9 images, 3 videos and 3 audio clips (each 2-15 seconds, 15 seconds in total).
The interactive client handles uploads, task creation, polling, and video playback when JavaScript is available.
What the video workspace supports
Model and format control
Choose available video models, output ratio, resolution, duration, and optional workflow flags before submitting.
Reference limits by model
Seedance 2.5 supports up to 30 images, 10 videos and 10 audio clips, each video or audio 2-30 seconds with a 30 second total. Seedance Mini, Fast and High support up to 9 images, 3 videos and 3 audio clips, each 2-15 seconds with a 15 second total.
Result review and iteration
Completed videos stay tied to the task history so creators can compare outputs and iterate without leaving the route.
Video generator questions
How do I reference uploaded assets in a prompt?
Type @1, @2 or @3 in the prompt to reference an uploaded asset. The prompt panel shows the reference limits of the selected model so you know how many images, videos and audio clips you can attach.
How many reference assets does each video model support?
Seedance 2.5 accepts up to 30 images, 10 videos and 10 audio clips, with each video or audio between 2 and 30 seconds and a 30 second total. Seedance Mini, Fast and High accept up to 9 images, 3 videos and 3 audio clips, with each between 2 and 15 seconds and a 15 second total.
What is visible to crawlers on the video generator route?
The static route explains the input types, generation flow, and membership connection even though the actual task controls are interactive.
Why keep a static version of an interactive generator page?
It gives search engines a stable explanation of the tool, the route purpose, and related navigation instead of a nearly empty shell.