Seedance 2.5 London Creator Night

​The first London community for Seedance 2.5. Thirty seconds, native 4K, fifty reference inputs — come and find out what it does to your work.

​BytePlus's Seedance 2.5 generates thirty seconds of native 4K video in a single pass, with audio built in the same latent space as the picture — so sound lands on the action without anyone syncing anything.

​The part most people haven't caught up with yet is the reference inputs. Fifty of them, against twelve in the last version, and not just images — audio, style references, 3D white-box models. That's the difference between prompting for a look and actually holding a character, a product or a brand steady across a sequence.

​We're the first community in London building around it, and this is the first night. The BytePlusteam are coming over, and the room is the people who'll push the model hardest.

​What's happening

• ​A technical walkthrough from the BytePlus team. Twenty minutes on how Seedance 2.5 actually works, what the fifty-reference pipeline makes possible, and where it still falls over.

• ​Hands-on generation. Bring a laptop and something you want to make. We'll be generating live, with the Lumina team on the floor.

• ​Drinks afterwards with people doing the same thing.

​Who should come

• ​Filmmakers, motion designers, 3D artists, agency creatives, and anyone building products on top of video models.

• ​You don't need to have used Seedance before. You do need to bring something you want to make — the point of the evening is leaving with a first version of it.

• ​20 spots limited.