ATOM

Personally, I don't agree. I find that 720p is far too low. It might be acceptable for small social media projects, but for any kind of professional use, 1080p remains essential, whether for zooming into the image or other adjustments. We aren't talking about videos shot with a camera here; we're talking about generation. If we can generate content natively in 1080p, it will always be better than performing an upscale.

Hot take: 1080p generation is usually unnecessary. 720p is faster, cheaper, and gets you where you need to go, you can also iterate cheaper and faster when it’s scale projects. I’ve been doing this for years now and almost never generate in 1080, I see almost no difference, 480p sure, but that’s pre-vis for a reason. Generate there or 720 and save, upscale after with @Magnific_AI or @topazlabs or someone else you like when project is done, then move on. Don’t let excitement of promised quality be the enemy of efficient spending. ❤️ I know that is not the sexy take from someone running an AI business now, 🤷‍♂️ but I am not interested in pushing waste just to burn GPU and charge more, F that. My goal is to help people make better work, save money, and keep quality high, while being excited as f^ck about what they are able to make.

@hectorVFX Crazy!

Houdini + ComfyUI + Flux Klein + LTX 2.3 Uno de mis primeros experimentos utilizando VFX como guía para generar un "render" usando IA en local.

@LudovicCreator @koldo2k Good job 💪

From Chemistry to Creative AI: My Journey to Becoming an Adobe Firefly Ambassador : A few years ago, I was still working in a chemistry lab. Test tubes. Molecules. Experiments. Today, I’m working with AI, cinematic visuals, and creative pipelines for film productions. And I’m incredibly proud to be part of the Adobe Firefly Ambassador Program. All the visuals in this thread has been in Adobe Firefly. Here’s the story behind that journey 🧵 Learn more about the Adobe Firefly Ambassador Program and sign up for the waitlist here on the thread 👇 This post is sponsored by Adobe Firefly through a paid partnership, showcasing my experiences as a Brand Ambassador for their innovative platform. All opinions are my own. #AdobeFireflyAmbassadors #Ad #MyAdobeAmbassadorStory @Adobe @AdobeFirefly

@MaxVOAO 👌😍

Liberty

@karim_yourself My last try !

Working on something big ⚫️ Made with Seedance 2 (coming to LetzAI soon)

@javilopen Haha, still way to much censore, it’s impossible to release Seedance 2.0 like that! Fingers crossed they release the content flag at launch. It’s a shame to have so much power so restricted.

Try it if you have access. It's a bit less restrictive now 😉

Today's a good day to brag about my colour pencil drawing

> tomorrow

@DavidAriew Very cool dude ! 💪

Yes, AI is here and 3D artists have to adapt. Here's one way I'm integrating AI with my 3D work, as a set extension. The BG is generated by Kling 3.0 and brought into my 3D scene so I can fully control the timing of the lights in the FG, which is 3D. Seedance 2.0 next!!

@PurzBeats All the people saying Hollywood is dead are shitty people. AI can be amazing in production, but for now it’s corrupted by people just chasing money with rage bait. The true users of AI won’t come from X. There are too many extreme voices there, both pro and anti AI.

I personally dislike the narrative that "HoLlYwOOd iS cOoKed" The most interesting AI work to me isn’t the stuff that looks finished. It’s the stuff that looks alive. In my opinion - AI isn’t a replacement pipeline. It’s a new creative instrument.

I can’t decide what pains me more… The people who hype AI as the death of Hollywood VFX, or the VFX artists trying to convince themselves that AI is useless and not currently being used in production. There is a serious reality distortion at both ends.

@DavidAriew David Ariew + seedance 2.0… I need to see that !

Badass! Abstracting scenes like this gets me excited to try it out! This feels more like art imo.

Hear from the effects supervisors of "Avatar: Fire and Ash" on how puppeteering and animation work together to bring the film's creatures to life. Listen to the full @officialavatar conversation on the Filmmaker Toolkit podcast.

@javilopen I’m very excited and interested to see what google is cooking with veo4 ! Seedance 2.0 look like a jump of 3 years in the future ahah

Seedance 2.0 has completely turned the film entertainment industry upside down. YOU CAN SMELL THE FEAR: - They're trying to block the meme-jokes we're generating on social media (like the 15-second Lord of the Rings one, which, at the end of the day, is parody, uses zero real footage from the movie, and would therefore fall under "fair use"). - Disney has sent a "cease and desist" to Seedance 2.0 (yes, to the Chinese! Hahahaha, I can't help but laugh). They're gonna wipe their ass with it. - The actors' union in the USA has published the cry-baby statement below against Seedance 2.0. And all of this because the jump in quality... IS TOO MUCH. The model is TOO good 😂 Like, scary good. Even the most hardcore, lifelong anti-AI accounts aren't saying a word these days. Because there's just nothing left to say: yes, of course, it still has small imperfections, the dialogue is still kind of a joke, etc... but... If we're not "there" right now, even the most hardcore deniers can see we clearly will be in less than 1 or 2 years. All these tantrums seem to be missing something important: One thing they don't seem to realize is that, right now, in pretty much any jurisdiction, it's perfectly legal to train models on any kind of data, whether you own the copyright to that data or not. So Disney or SAG-AFTRA can try whatever they want, and not only are they gonna get nowhere because this is China, but even in their own jurisdictions, what xAI, Google, OpenAI, and everyone else is doing indiscriminately is: it's COMPLETELY LEGAL to train on any data. That said. OBVIOUSLY, if a user then tries to publish generations that use someone else's IP (like Superman), that's a different story, obviously: the IP itself is protected. Same as if you'd drawn it by hand. So yeah, well... It's a new world. But careful, nobody should be surprised by this... except the deniers, of course. Denial is no longer an option. Put differently, SAG-AFTRA is judging ByteDance (Seedance 2.0) with a double standard: American models like Sora also trained on whatever data they felt like. If anything, a few days after launch, they slightly tightened the rules about not using celebrities, etc. (but that's basically makeup, at the level of detecting it in the prompt and stopping you: the underlying model is fully capable of doing it). This is what ByteDance will end up doing too, if they feel like it, because there's also no law forcing them to. And by the way, when there are open-source models at this level and you can run them at home... all restrictions of any kind are over. The toothpaste is out of the tube, and there's no putting it back in. That said, I'll repeat it. If a user generates Brad Pitt, they could get sued over rights if they publish it anywhere, unless they can defend it as parody and "fair use". Same with IPs like Batman, etc. So where should protection of IP and likeness rights come from? Where it has always come from: from the channels/platforms where you publish it, if it doesn't fall under "fair use". If you generate your movie and Superman shows up, you're screwed, because it's protected IP and they can take it down from YouTube or wherever you publish it at any time. But again: how are they supposed to fence this in if you generate it for yourself, at home, with your open-source model and your GPUs, in a near future where everything is more efficient and less expensive? If you have your own "personal Netflix", we're entering completely uncharted territory that they can't realistically stop 🤯 The alternative is not going to happen. The alternative would be to legally limit what data models are allowed to train on, which in practice is: - First, almost technically impossible: if, for example, you wanted to limit a model's training data around "Superman", it would be almost impossible or extremely expensive because Superman images and videos are everywhere, not just in official DC Comics material, but also in fan art, user posts, and so on. So, in practice, they'd have to use other models (trained on everything) to scan the dataset before training the final model to detect whether certain things are present or not (which turns into a logical absurdity, a snake eating its own tail). What they *can* do is, for smaller artists whose work is concentrated in a few places, offer an "opt out'" which many jurisdictions already contemplate, and remove that URL/data from training... but all it takes is one of their images or videos being copied somewhere else and, in practice, it becomes impossible or very costly to reliably separate. - Second: no nation/country/power bloc (except Europe, which is off in la-la land trying to figure out whether to put caps on plastic bottles or not) is going to want to lose THE AI RACE. Losing this race is LOSING EVERYTHING. Because the first nations to pull it off (and it's clearly going to be China and the USA) will dominate the world. So they're not going to pass legislation that kneecaps them, because they don't want competitor nations to beat them. So they'll keep legally allowing their companies to train on any data they want. So. Interesting time frame you are living in, eh?

@MEYARachad giga chad

@javilopen What have you done, javi

monday is the day MUFV WE ARE SO BACK

@fofrAI You are one of the most creative guy i’ve seen using AI ! 👌

Don't touch the pickles: they've gone bad. Check out Rodeo FX's spectacular #VFXbreakdown of its creature effects from horror series #WelcometoDerry Watch the full video on the Rodeo FX YouTube channel: youtube.com/watch?v=yygZil… #VFX #creaturedesign #RodeoFX

@Maxlanderfr @FearedBuck J’ai eu accès à ce modèle! Mais j’ai juste eu le temps de faire ce test là! Assez fou

@FearedBuck @ATOM_VISUAL on arrive à des folies! Exactement ce que tu dis depuis des mois. Et les gens, allez le follow sur YouTube aussi 😉

An AI-generated video of Brad Pitt and Tom Cruise fighting in a rooftop is going viral, with people saying AI is getting too realistic

Finally tried Seedance 2.0👇 It's coming to LetzAI later this month, so stay tuned.