Live data from Hacker News

Seedance 2.5

seed.bytedance.com

181–190 of 278 posts

Re: Seedance 2.5

#181
post #37

The quality is quite high, but an observation is the direction they're taking these models correlates heavily to the usage demand of China vs the West. Specifically, they're immensely focused on t2v for action / high effect shots. There's one human reference shot in the entire release page, and that one doesn't focus on dialog at all. For filmmakers I've talked to in the US, one of the biggest demands they have is v2…

I hear this a lot, but I observed this is no longer that simple. Like Green Book (2018) made over US$70.7 million in China. And one of the most popular films in 2021 was Hi, Mom (2021), made over US$785 million. Obsession (2026) is another one that is doing amazing in China, absolutely beating high action films like Supergirl ($12 million and going vs less than $1 million)

> Obsession (2026) is another one that is doing amazing in China

I haven’t seen the movie yet but I’ve been a subscriber to the YouTube channel of Curry and Cooper [1] for a long time. I’m looking forward to watching the movie.

I wonder how many of the other people that went to see Obsession were already fans of Curry and Cooper.

[1]: https://www.youtube.com/@thats_a_bad_idea

Re: Seedance 2.5

#182

23 Jun 2026 03:31:03 UTC Seedance 2.5, generating a complete 30-second video in one go https://twitter.com/xiaohu/status/2069236441964818508 https://news.ycombinator.com/item?id=48639900 [ok] 23 Jun 2026 03:53:32 UTC Seedance 2.5 pushes AI video toward references and control https://news.ycombinator.com/item?id=48640057 [flagged] [dead] 23 Jun 2026 04:47:30 UTC SeeDance 2.5 Is Stunning https://twitter.com/Long4AI/sta…

Why amplify the copycat spam domains?

Re: Seedance 2.5

#184
post #37

The quality is quite high, but an observation is the direction they're taking these models correlates heavily to the usage demand of China vs the West. Specifically, they're immensely focused on t2v for action / high effect shots. There's one human reference shot in the entire release page, and that one doesn't focus on dialog at all. For filmmakers I've talked to in the US, one of the biggest demands they have is v2…

China has a population 4 times bigger than the US, and the films you cite did roughly 4 times better in each example.

Re: Seedance 2.5

#185
post #24

I don't think audio, image or video generation should exist. I haven't seen enough positive applications to justify the amount of harm these tools are being used to cause.

[flagged]

It's going to be just like social media. A flood of content from the talentless masses exposing us to their lazy and shallow ideas they just cannot keep to themselves. Once in a while a diamond in the rough will be found, but at what cost?

Re: Seedance 2.5

#186

Earlier quoted context omitted.

[flagged]

Some voices are “$politicalParty should win at all costs” and “my ex-spouse should be humiliated” and “my boss should go to jail for the pittance they pay me”, and instead of text opinions posted or voices shouted, there’s video gen to amplify them. They didn’t have the skill to make a convincing fake video themselves but if tools are at their fingertips… temptation. Really not ideal although obviously amazing artist…

[flagged]

Re: Seedance 2.5

#187
post #37

The quality is quite high, but an observation is the direction they're taking these models correlates heavily to the usage demand of China vs the West. Specifically, they're immensely focused on t2v for action / high effect shots. There's one human reference shot in the entire release page, and that one doesn't focus on dialog at all. For filmmakers I've talked to in the US, one of the biggest demands they have is v2…

China has a population 4 times bigger than the US, and the films you cite did roughly 4 times better in each example.

But how much does ticket cost in China compared to the US? (Genuine question)

Re: Seedance 2.5

#188
In second video, Look at the reflection of the staff member headset :)

Such models will have fascinating use-cases. But "generating realistic content" is a comedic resemblance of realism movement in painting.

Re: Seedance 2.5

#189
post #24

I don't think audio, image or video generation should exist. I haven't seen enough positive applications to justify the amount of harm these tools are being used to cause.

While I generally think it's balanced against a lot of negative applications (misinformation, deepfakes, etc.), there are some good applications. I think regulation just hasn't sufficiently caught up with the harm they can cause. To give a good use case (audio generation specifically), the 2002 game Morrowind has had a resurgence lately and it's a really great game, but it lacks fully voiced lines for dialogue. A com…

Morrowind wasn't meant to be narrated, NPCs blur out walls of text with hyperlinks in them leading to more walls of text. If I had to sit idle while someone/something was reading all of this to me, I'd be bored out of my mind.

Re: Seedance 2.5

#190

Earlier quoted context omitted.

While I generally think it's balanced against a lot of negative applications (misinformation, deepfakes, etc.), there are some good applications. I think regulation just hasn't sufficiently caught up with the harm they can cause. To give a good use case (audio generation specifically), the 2002 game Morrowind has had a resurgence lately and it's a really great game, but it lacks fully voiced lines for dialogue. A com…

> They don't take away jobs from artists Does the game with improvements now better compete against other games with paid human voice actors?

The game is from 2002. Anybody wanting to play the game either buys it for nostalgia or as an enthusiast. All the mod does is increase accessibility.
Post reply on HN