maps_mc
24 posts
These AI UFC edits are so good.
The UFC should just embrace this and create a full AI special.
English
@maps_mc Hello!
I just tried an old NSFW prompt and had no issues generating it.
You could try it yourself since they might still be giving away a $5 credit: venice.ai/chat?ref=HHQ-1D
You have to go to the following portal to load it up: venice.ai/lp/seedance/ge…
English
Update.
I was wrong. The model isn't getting worse for everyone, and instead only for me and a few others.
Bytedance has specifically targeted our accounts through platforms like Venice. I made a new account from scratch, and all of a sudden I could generate old prompts again.
English
@wildmindai It will not run on consumer GPUs (certainly not at full precision and likely not at reasonable quants and inference times) but it won't matter because it won't be open weight anyway.
This model is too good, stop dreaming. It's closed and likely huge.
English
HappyHorse-1.0 vs All.
- 720p, 24fps
- crisp
- pleasant colors, no AI-ish vibrancy
- nice textures, good skin
- dynamic
- good prompt following
If this model runs on consumer GPUs - it'll be an absolute nuke
Artificial Analysis@ArtificialAnlys
We’ve added a new pseudonymous video model to our Text to Video and Image to Video Arenas.‘HappyHorse-1.0’ is currently landing in the #1 spot for Text and Image to Video (No Audio) and the #2 spot for Text and Image to Video (With Audio). Further details coming soon. Example generations below from HappyHorse-1.0 in the Artificial Analysis Video Arena 🚀
English
@Megatron_ron boxers one of the pilots underwear, they are claiming to have gory photos of the American dead bodies but haven't posted them yet.
English
Seedance 2.0’s public API timeline has been delayed. The API was aiming for Feb 24, but it’s getting pushed (no new date yet).
Been chatting with the ByteDance team on the integration side and confirmed it.
They’re likely putting stronger copyright/deepfake guardrails in place first — tighter filtering, blocking unlicensed real-person likeness videos, plus compliance monitoring — before opening it up more broadly.
English
@thecoolman14136 @alisaqqt Hollywood its just dumb, they should try to negotiate with Bytedance to have some exclusivity deal or something like this instead of trying to sue. I hope this year some OSS model releases and have the same quality level as Seedance 2
English
@comunidademc Alguem leva uma JBL e coloca pra tocar Aria Math enquanto não começa o filme.
Português
@Izadora_Sirno Não ligue pra essas coisas, a pessoa que faz isso tem algum problema com si propria, não com você.
Português
É tão triste ser julgada por uma deficiência q eu n posso mudar
Ninguem tem um pingo de empatia
Português
@hypoparams @shlomifruchter Possibly by using some conditional guidance that "counts" how many of X object in the scene
English
@shlomifruchter these are impressive -- peculiarly, in the strawberry vids (both yours + the inspo) extra strawberries appear to float up from the bottom. is this a kind of thing that can be mitigated through prompting?
English
@Siddharth87 They should start creating a explicit 3D particle system predictor and renderer, because if not problems like the ballerina will always happen.
English
Google continues to destroy OpenAI this week with their product launches. The latest and most incredible one being Veo 2, their text to video model.
What’s incredible about Veo 2 is not just that it can generate up to a full minute of video from one prompt at 1080p, it’s also that the videos look completely natural, like they were shot with a film crew.
Have a look at the clips below, all generate by Veo. You’ll notice it gets even the little details right - the way the car kicks up dust, the consistency in the ballerina as she moves, the way the tomato slices fall off.
A year ago these models struggled to create a realistic and consistent 10 second scene. Now it’s generating what could be an entire ad or video game cut scene. In a few months we’ll see Ai-generated video clips in movies and tv shows.
Have you tried Veo 2 yet? What do you think?
English
@VahidK Can O1 work the drive-thru window at a McDonald's?
English
In my opinion we have already achieved AGI and it’s even more clear with O1. We have not achieved “better than any human at any task” but what we have is “better than most humans at most tasks”. Some say LLMs only know how to follow a recipe. Firstly, no one can really explain what a trillion parameter deep neural net can learn. But even if you believe that, the whole scientific method can be summarized as a recipe: observe, hypothesize, and verify. Good scientists can produce better hypothesis based on their intuition, but that intuition itself was built by many trial and errors. There’s nothing that can’t be learned with examples.
English
The company I work for, Silverside AI, just created an ad for @CocaCola (yes THE Coca-Cola)!! We were asked to bring the classic Coca Cola Holidays are Coming ad back through the use of AI. Check it out:
English
@allanldsantos @kimpaim Tá bloqueado só no Brasil né, por que eu tô vendo aqui com a vpn.
Português
@kimpaim Você está celebrando a manutenção dos bloqueios das contas também?
Português
