ByteDance
Oct 28, 2026

Seedance 2.5 adds 4K video output, with first access limited to 20 film teams worldwide

ByteDance’s Volcano Engine has rolled out a 4K version of its Seedance 2.5 video generation model, but the release is starting with a tightly controlled trial. According to the company and a report cited from Sina Tech, the first batch is limited to 20 film studios and directors worldwide, leaving ordinary users and most developers without access for now. Volcano Engine has not disclosed pricing, the maximum length for a single generated clip, or a timetable for broader availability. The 4K upgrade had been previewed when Seedance 2.5 was first introduced at Volcano Engine’s FORCE conference on June 23. Even so, public access remained capped at 1080P for months, and that 1080P option itself only opened on Aug. 17 after earlier availability at 480P and 720P. The company said the new version has been specially trained to better capture facial expressions, subtle motion, and fine visual detail, while also improving quality retention when reference materials are used. Sina Tech reported that 20 projects are already using the 4K version, with the earliest output expected to air on Chinese satellite television in November. The report also said the lineup includes major international film projects.

1850
Seedance 2.5 adds 4K video output, with first access limited to 20 film teams worldwide
ByteDance
Sep 22, 2026

ByteDance adds Draft mode to Seedance 2.5 API for lower-cost 480P previews before 1080P output

ByteDance has launched a Draft preview mode for the Seedance 2.5 API, letting users generate lower-cost 480P sample clips before committing to a 1080P final version. The workflow is aimed at reducing the expensive trial-and-error phase common in AI video generation, where users often need multiple attempts before landing on a satisfactory result. According to the description in the source, the feature is also available in Jimeng under 「Seedance 2.5 (Draft Mode)」. The process differs from simply testing a prompt in low resolution and then rerunning the same prompt in high resolution. When a user chooses to render in 1080P, the model links the selected draft clip’s ID and reuses parameters including the prompt, reference materials, seed, aspect ratio, and duration for a new inference pass intended to preserve the original structure, framing, and motion. The source also notes that the output is not a frame-by-frame replica, nor a basic super-resolution upgrade from 480P to 1080P, because local textures, small text, and crowd counts may still change. Official estimates cited in the report say a 5-second 1080P video without video input can cut costs by 57% and nearly double generation speed if users need four tries on average; if 20 tries are needed, savings can reach 77%.

1300
ByteDance adds Draft mode to Seedance 2.5 API for lower-cost 480P previews before 1080P output
Seedance 2.5
Aug 3, 2026

Seedance 2.5 handbook highlights longer video generation, timestamp control and multi-reference editing

Seedance 2.5 has rolled out in full, with the official Feishu handbook laying out a broader set of controls for AI video creation than the previous 2.0 version. The update raises native single-pass generation length to 30 seconds, allows repeated extensions to 60 seconds, and adds an ultra-long mode that supports up to 180 seconds. The documentation frames that shift as a move away from generating isolated clips and toward producing more complete narrative sequences in one workflow. The handbook places timestamp-based prompting at the center of the update. Users can specify second-level time windows to direct motion, camera movement, scene transitions, sound and dialogue, then make targeted edits to selected segments after generation while keeping continuity across the rest of the clip. It also expands multi-modal reference handling, with guidance to upload references by priority and explicitly assign each image, video or audio sample a role inside the prompt. Other changes listed in the manual include cleaner default outputs with fewer unwanted subtitles and background music, stronger physical realism, more consistent cuts, smoother handling of complex actions, support for mainstream foreign languages through direct prompting in the target language, and a recommended workflow built around planning, reference preparation, scripting, generation, localized edits and final post-production.

1420
Seedance 2.5 handbook highlights longer video generation, timestamp control and multi-reference editing