Generate Seedance 2.5 videos up to 30 seconds with image, video and audio references, synchronized sound and flexible aspect ratios. Start with free credits below.
Enter a prompt, add optional references, choose a ratio and duration, then generate your video online.
New accounts get free credits to try Seedance 2.5. Usage is credit-based and is not unlimited.
Seedance 2.5 is live
Seedance 2.5 is selected by default in the generator. You can also switch to Seedance 2.0 or Seedance 2.0 Fast when you want a different balance of speed, resolution and credit cost.
Seedance 2.5 is available with credit-based pricing. Your cost depends on video duration, resolution and reference media.
Seedance 2.5 is ByteDance's latest AI video model and is available in the generator on this page.
It can generate a continuous video up to thirty seconds, reducing the need to stitch several short clips together.
Multimodal references let you combine images, video, audio and text to keep characters, products and visual style more consistent.
Seedance 2.5 is released and available to generate online on Seedance2.
ByteDance unveiled the model at the Volcano Engine FORCE conference, alongside a 4K upgrade for Seedance 2.0.
Seedance 2.5 went live on Jimeng AI and Doubao Pro, rolling out gradually rather than to every account at once.
Seedance 2.5 is available in the generator above and selected by default.
Use the Seedance API to generate Seedance 2.5 videos from text prompts and multimodal references.
These are the Seedance 2.5 capabilities that matter most when creating a video.
Create a Seedance 2.5 video online in four steps.
Name the camera, the subject, the action and the mood. Vague prompts drift; "handheld mini-DV footage, slight hand shake, natural zoom" gives the model something to hold onto for thirty seconds.
Upload a first frame, a first and last frame pair, or a set of reference images. References are what keep a character recognisable from second one to second thirty.
Pick the aspect ratio for wherever the video will be published, then choose resolution and duration. Higher resolution and longer clips cost more credits.
The AI video generator runs each request as an asynchronous job. Watch the back half of the result closely — that is where consistency problems show up first.
Seedance 2.0 is not obsolete. As an AI video generator it is faster, cheaper and available everywhere, and for clips under fifteen seconds the quality gap is smaller than the marketing suggests.
| Capability | Seedance 2.5 | Seedance 2.0 |
|---|---|---|
| Max single-pass length | 30 seconds native | Up to 15 seconds |
| Reference inputs | Up to 50, multimodal | Images, first and last frame |
| Resolution | Up to 720p now; 4K planned | Up to 4K |
| Audio | Synchronized in one pass | Native audio |
| Regional editing | Yes, redraw part of a frame | Not available |
| Availability | Available online and through the API | Widely available, API ready |
Pick Seedance 2.5 when the shot has to be one continuous thirty-second take, or when many references need locking at once. Pick Seedance 2.0 when you want speed, lower cost, predictable availability, or API access today.
Every page about this AI video generator lists the wins. These are the failure modes creators are actually hitting, and they matter more for your budget than the benchmark numbers do.
What creators are actually building with this AI video generator in its first week.
Every clip below came out of the AI video generator on this page — no stock footage, no borrowed samples.
These clips were generated with Seedance 2.0. Seedance 2.5 examples are being added and will be labelled separately.
Independent creators putting this AI video generator through real tests — worth watching before you commit credits to a long generation.
Videos are published on YouTube by their original creators and embedded here.
Use the Seedance 2.5 API to add text-to-video and multimodal video generation to your product.
Yes. Seedance 2.5 is available in the generator on this page and is selected by default.
ByteDance released Seedance 2.5 on July 31, 2026. It is now available to generate online on Seedance2.
Thirty seconds in a single native pass, without stitching. An ultra-long beta mode extending single generations to around 180 seconds has been spotted in ByteDance's own app, but it is not generally available.
Seedance 2.5 is free to try with new-account credits. Each generation uses credits, so there is no unlimited free plan.
Yes. The Seedance API supports the seedance-2.5 model for text prompts and multimodal reference inputs.
No. It is a proprietary ByteDance model. There are no official weights on GitHub or Hugging Face, and repositories claiming to expose a Seedance 2.5 API are unofficial.
Use the 2.5 model for continuous thirty-second takes and heavy reference control. Use Seedance 2.0 for speed, lower cost, wide availability and API access. For clips under fifteen seconds the difference is smaller than it looks.
Long-form consistency is the weakest area. Objects vanish, scale shifts and lighting jumps after the first ten to fifteen seconds. Pin anything important with reference inputs, keep the camera move simple, and consider generating in shorter segments when every beat has to be exact.
Start with free credits and generate a Seedance 2.5 video up to thirty seconds directly in your browser.