Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • Any tutorial for me to learn how to use
    by nfnmema
  • Try this prompt with claude code "download the new minimax h3 model and render a test movie with it"
    by jclarkcom
  • I've said it before and I'll say it again, human directors are still valuable, as they use AI video editing tools to generate the shots they want and put them together in a cohesive way. Previously they might've used film and actors but if they can just prompt the AI (or create workflows as seen with ComfyUI) then they arrange them together just like how an EDM producer doesn't actually play the instruments but instead the creativity is in the arrangement.

    I suspect it'll be quite a while until AI gets a good enough aesthetic sense to do this, as even with static HTML websites humans can easily see that it's AI slop.

    by satvikpendem
  • outdated take

    there are sequencing AI that will edit

    case in point, the entire SaaS multimedia space has pivoted this year to agentic workflows, as in, no more generating AI for that sensitive audience, but instead automating the human work of editing and compositing of real media

    if you so happen to supply generative media it will form a cohesive edit of that too

    also website slop is distinct from the AI generated sites that blend in. you only notice the ones that don’t.

    by yieldcrv
  • or option 2 we'll keep making productions with film and actors. I get it's easy to feel that it's all over with how good these video models are getting but thinking we'll all be slaves to the slop machine once it gets good enough is pretty pessimistic depressing and IMO unlikely.

    (I do think it will get a foothold in the "crap people are ashamed to admit they watch" sector though, which it basically already has)

    by unleaded
  • Seedance 2.5 just came out and it is incredible，significantly better than this for a lot of cases. This one is the latest _free_ video generator.

    But as far as your composition tools, they are already available.

    by ilaksh
  • This is an interesting problem. A similar approach that worked for us was to only load the tools the agent actually needs for each task.
    by torment-nexus
  • Has anyone tried running this on Mac device? (e.g. Mac Studio Ultra)
    by mihau
  • Failed with a software error for me
    by Havoc
  • Reference-to-video mode seems like all that was missing to enable completely independent cinematography as right now one couldn't stitch different scenes together properly without altering substantial portions of the scene.
    by storus
  • I saw the samples people have posted. Immediately deleted LTX2 and WAN folders. Those are completely worthless now.

    There is some debate on the license for those in the US, UK, EU, plus… no comment other than whew those samples though!

    by SV_BubbleTime
  • "Regions such as the EU, UK, South Korea, and the US are currently developing or enforcing AI-related regulations that may have specific implications for generative video models"

    You just have to pinkie promise you won't make disney mad and they will send you a licence https://huggingface.co/MiniMaxAI/MiniMax-H3/blob/main/docs/Q...

    by Maxious
  • On one hand: impressive. On the other hands aesthetically it all looks painfully bland and generic.
    by fodkodrasz
  • This, today, is the absolute worse this model will ever be. Chill.
    by SV_BubbleTime
  • I agree. But is that the model or the prompt?

    I remember reading a report where people running AI-model instagram account were using insanely long and detailed prompts about the setting, lighting, makeup, pose, disposition, clothing, etc. about their models. Presumably with some reference image of the face / body to remain consistent across images.

    It‘s not clear to me whether a sufficiently detailed prompt can generate actually interesting video with a natural ”texture” (for lack of a better word).

    by _diyar
  • > The result gives a total memory footprint reduced by 66%, from 123.6 GB in full precision to 42.5 GB with the smallest models variants. Combining this with our dynamic VRAM offloading enables a next-generation 2K video model to run locally on a GPU like the RTX 3060.

    Pretty cool.

    But assuming you have a 16GB 3060, how long would it take to generate a 15 second clip?

    by Mashimo
  • Around 10 minutes.
    by ranyume
  • I don't believe the 3060 has a 16gb variant, only 12 and 8
    by truthbe
  • The mouse render is surprisingly good. Several of those clips stood out to be a pretty big leap in terms of current SOTA models.

    The only one that looks "off" is the beverage ad video during the can opening clip, it still has that "AI smoothening" effect. Good thing this can be done pretty well using traditional rendering.

    I feel like for a good while now we'll transition into a process that uses traditional "close-up" rendering/shots + AI generated wide-shots or quick cuts.

    Exciting, but also troubling. This being open-weights is a massive win for the community though.

    by sheesdev
  • right before that, there's the part with the person hiking up the dish and 'breathing', and the clouds of water vapor coming out of their mouth don't line up with their breaths

    devs pls fix

    by jareklupinski
  • This is still about a year and a half behind Seedance 2.0/ Seedance 2.5

    But it represents a coming price pressure that will face the leading foundation models. Open source will prevent runaway costs.

    Moreover, it prevents the hair-trigger platform safety checkers from shutting down creative work. Video models are notoriously bad at shutting down a huge number of requests.

    Creatives will prefer to work on cloud or private GPU clusters. Waiting 10 minutes for a few seconds of 480p is unacceptable. Hobbyists will have fun, but most actual production work is happening in the cloud.

    Artist's time is worth money, and they like to spin up dozens of concurrent generations at a time to more quickly explore the generation state space and make progress on completing work.

    by echelon
  • I dug up a few old parody ideas I’d had back in high school and threw them at MiniMax M3 on my RTX. There’s definitely still a lot of jank once you move away from fairly normal scenarios. The moment you start to veer into weirder concepts, things tend to break down a bit especially in the game show where someone is strapped to a wheel and being spun.

    Still tho, I was actually shocked by how well the text-to-video turned out overall, and how fast it ran. A 10-second, half-megapixel video gen took only a few minutes which is kinda crazy especially thinking back early WAN days.

    Video demos:

    https://imgpb.com/rllwg

    by vunderba
  • Hilarious well done
    by keepupnow
  • That spinning person one would make an interesting benchmark. The model clearly has a strong prior that human heads go upright.
    by nl
  • Im running this on my 4070ti super (16 gb vram), and it takes 10 minutes for a 10-seconds 480p video. but the results are spectacular.
    by vblanco
  • How much RAM does your machine have?
    by 384028345
  • Huh, interesting. I tried to generate a 10 second 1080p clip on a bigger machine and the results were quite poor. Unusable for anything, in fact.
    by chrsw
  • 1 minute for a second of footage, that is awesome! Thanks for sharing.
    by robbru
  • If you wouldn't mind sharing, what's your Comfy workflow for this? I have the same video card setup and would like to give it a shot.
    by mwigdahl
  • I am particularly curious how multimodal models will work with types of knowledge that are inherently non-text. For example, SOTA LLMs really suck at electronics, especially analog electronics.

    Is MiniMax H3 capable of logical / technical reasoning, or is it purely art oriented?

    by ddevnyc