ByteDance has released a new version of its AI video generation model, Seedance 2.0. It supports eight languages, including Russian and English.

Made this in 30 minutes with Seedance 2.0.
We’re entering an era where one person can make a film. pic.twitter.com/Txpc83FRcM

— Rayleigh_AI (@Long4AI) February 8, 2026

Users can upload images, videos, audio, or text as references to create their videos.

“Set the visual style with an image, define character movements and camera angles using video, create rhythm and atmosphere by uploading a few seconds of audio. Combine all this with prompts to make the creative process natural, efficient, and truly cinematic,” the company stated in its announcement.

Seedance 2.0 is available in the Chinese version of the Dreamina service. Access can be obtained through a Douyin (local TikTok) account. By the end of February, the model will be available on CapCut, Higgsfield, Imagine.Art, and other third-party services.

Seedance 2.0 is insanepic.twitter.com/oBqAm3zsBZ

— Angry Tom (@AngryTomtweets) February 7, 2026

Users who tested the neural network noted its high directing and editing skills, as well as “incredibly natural, almost professional” transitions between scenes.

“There are features that seem illegal: you upload a script, and the program generates scenes (not just clips) with visual and sound effects, voices, music — all beautifully done,” emphasized a user with the nickname el.cine.

seedance 2.0 is the only model that makes me so scared

literally every job in the film industry is gone, you upload a script, it generates scenes (not just clips) with vfx, voice, sfx, music all nicely edited, we may not even need editors anymore

and now I understand why it’s not… https://t.co/YUQAYuMhh8 pic.twitter.com/UYsP5fGMo6

— el.cine (@EHuanglu) February 8, 2026

ByteDance's release has triggered a surge in stocks of Chinese media and AI companies.

Source: Bloomberg.

COL Group hit the daily trading limit of 20%, while Shanghai Film and Perfect World each rose by 10%.

Recall that in February, Chinese developer Kuaishou introduced the third version of its video generation model, Kling AI.