On July 31 ByteDance released Seedance 2.5 — the next generation of its flagship video model. At first it was only available in the company's Chinese products — the Jimeng AI web app and the Pro tier of Doubao — but with the API now open, the model has already landed in GPTunneL: generate right in the lab, no VPN needed, pay only for what you use. Here is what the model can do, with the official demos.
Release timeline
The model was announced on June 23 at the Volcano Engine FORCE conference in Beijing, then still in enterprise beta. A limited public test ran in early July, and the consumer launch followed on July 31 — China first. Alongside it, Seedance 2.0 gained 4K output.
The headline: one-take video up to 30 seconds, with sound
The key difference from Seedance 2.0 is duration. The model generates a continuous clip of up to 30 seconds in a single pass, with no stitching of short fragments — and the audio is generated together with the video in that same pass, not layered on top of a finished clip. For comparison, most competitors top out at 8–15 seconds per generation.
The flagship demo is a 30-second one-take: a character in a black coat walks through six connected rooms, each shifting the style and mood of the shot. Another example is a full music video with a single performer, built from one prompt using appearance and wardrobe references — no timeline, no keyframes. And to show the full pipeline, ByteDance released "The Missing Pair", a short film made entirely with Seedance 2.5.
Multi-round extension grows a clip while keeping characters, environments and pacing, and a beta Ultra-Long Video mode spotted in the Jimeng app goes up to 180 seconds.
Here is what that looks like in the official demos. A dance in front of a wall of fire — one continuous shot with music and motion generated in a single pass:
And a 30-second mini-story of a suitcase travelling through an airport — camera, light and "cast" keep changing while the object stays consistent the whole way:
Up to 50 references per generation
Seedance 2.5 accepts up to 50 multimodal inputs: 30 images, 10 videos and 10 audio tracks. Two stand-outs:
- clay-render references (white-model control) — untextured 3D blocking of a scene that pins down poses, motion paths and camera angles; per ByteDance, the model then builds physically correct light on its own — direction, color temperature, shadows;
- audio as a reference — the model can follow an uploaded soundtrack, matching pacing and motion to it.
According to Artificial Analysis, Seedance 2.0 already led the image-to-video leaderboard among models with audio — 2.5 builds on that base.
Editing without reshoots
The second big theme of the release is editing finished clips:
- timestamp edits — "replace the background from second 12 to 18";
- green-screen background replacement that adapts the subject's physics and lighting;
- re-shooting the camera move on an existing clip;
- local edits of a frame region from a reference — without regenerating the whole video.
Realism also takes a visible step up: textures, skin, light and facial acting look noticeably richer than in 2.0. Judge for yourself — a barbershop scene with two characters and a mirror (mirrors are a classic failure mode for video models):
To its credit, ByteDance admits that complex motion and scenes with several closely interacting subjects are still hard for the model.
How Seedance 2.5 stacks up
- Sora 2 is effectively out of the race: OpenAI shut down the Sora app and web version on April 26, and the API goes offline on September 24, 2026.
- Kling 3.0 — native 4K at 60 fps, but up to 15 seconds per pass.
- Veo 3.1 — the best synchronized audio with dialogue, but 8 seconds per generation.
Seedance 2.5's strengths are duration, reference-driven control and reshoot-free editing. This is a bid for a production workhorse, not just "the prettiest clip". The scale it can handle is impressive too:
Where to try Seedance 2.5
There are several options, and they differ a lot in how accessible they are:
- ByteDance's official apps — the Jimeng AI web app and the Pro tier of Doubao. Both target the Chinese market: the interface is in Chinese and registration requires a Chinese phone number.
- APIs for developers — Volcano Engine Ark in China and the international BytePlus platform.
- You can't download Seedance 2.5 — unlike open-weight models such as Kimi K3, ByteDance does not publish the weights. The model exists only in the cloud, so any "download Seedance for free" site is a fake at best.
- In GPTunneL — the model is already in the lab: open Seedance 2.5 and generate side by side with Kling, Veo and other video models. Signing up takes a minute, no VPN needed, local payment methods supported.
How much Seedance 2.5 costs
There is no free tier anywhere: the Chinese apps run on subscriptions and the APIs charge per token. For reference, Volcano Engine's rates are roughly ¥70 per million tokens without video input and ¥42 with it; on BytePlus — $10.70 and $6.40 respectively.
In GPTunneL no subscription is needed — you pay per second of finished video: from $0.21 per second in 480p and $0.46 in 720p. Draft an idea in 480p, then render the final cut in high resolution; the calculator on the pricing page gives an exact quote for your clip length.
Seedance 2.5 FAQ
Is Seedance 2.5 free? No. The Chinese apps offer it by subscription, the APIs charge per token, and in GPTunneL you pay per second of finished video with no mandatory subscription.
Can I download Seedance 2.5? No — the weights are closed, and the model is only available through cloud services. Any "free download" from search results is not Seedance.
How is 2.5 different from Seedance 2.0? The headline change is one-take clips up to 30 seconds with sound generated in the same pass (2.0 is shorter and has no native audio), up to 50 references per generation, timestamp-based editing of finished clips, and a visible step up in realism.
Do I need a VPN for Seedance 2.5? The official ByteDance products aren't available in every region and require Chinese payment services. In GPTunneL the model works right in your browser — no VPN needed.
Try it yourself
You can start right now: Seedance 2.5 in the GPTunneL lab. And here is what the Seedance line is capable of — a clip generated with the previous generation of the model:
Want to compare? The lab also offers the cheaper Seedance 2 with fast and mini variants. New models arrive here the day their APIs open — follow the news in our blog and Telegram channel.