Live data from Hacker News

MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

blog.comfy.org

91–100 of 100 posts

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#91
post #47
post #36

Earlier quoted context omitted.

Suck at what aspect of (analog) electronics specifically? Not contradicting the claim, just want to understand it. I have not tested yet, but I suspect that LLMs with a harness that can execute code can do SPICE simulations rather ok these days? I have seen MCPs for measurement equipment also, maybe they can even close the physical loop?

spice is a very bad simulation. it's not like a unit test or a VM. it works very differently to the real thing, only approximating it in some highly controlled situations.

It depends on how you hold it.

If you have accurate device models, and you know how to use simulations, you can predict quite well the behavior of the analog circuits that you design.

Simulations that work like the real thing are an absolute necessity in the industry. It is frequent to design the analog parts of some integrated circuit, when you might have to wait months to get prototype samples that you can measure in the laboratory.

If the prototypes do not work exactly as expected, you will probably have the chance to make once a correction of the schematics and/or layout, which will be incorporated in the final product.

But when not even the second try does not work as designed, that is likely to be a failure, because any other redesign would add months and many millions of $ until the product can reach the market.

So "spice" simulations that can be trusted are a necessity. When designing integrated circuits you cannot use empirical methods that work when you make manually a single-use board, where you can replace components or adjust resistors, capacitors or inductors until you get what you want. For integrated circuits, you must know in advance how the circuit will work, because you cannot tweak it.

It is true however that it is easy to configure simulations that will give non-sense results, due to lack of convergence or other numerical errors, so to avoid this, one typically needs both experience with laboratory measurements and experience in using the simulator.

I doubt that an LLM would successfully run SPICE simulations, because there are few examples of written instructions of how to do this in the right way (which varies depending on the domain of applications, and each SPICE-like simulator may have its own quirks).

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#92
post #31
post #26

Earlier quoted context omitted.

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 gener…

That would be the prompt. With the right assistance from Qwen3.5/Ornith I was able to achieve some amazing results. Unfortunately due to their licensing I'm not allowed to use it in the USA, so I had to halt testing.

[dead]

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#93

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 inste…

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 s…

I'm familiar with the space, my point is it's still not as good, in the same way that AI generated webpages are still not as good. Cohesion is the main issue, usually AI generates too many disparate elements.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#94

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 inste…

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)

Just like there are still plays even though movies overtook them as the main form of entertainment with acting, so too will AI generation overtake movies with real people. It's simply cheaper and more freeform creatively to use AI so expect that to be the future.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#95
post #85

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 tur…

That spinning person one would make an interesting benchmark. The model clearly has a strong prior that human heads go upright.

Oh yeah definitely agree. I think one of the older tests for LTX and WAN text-to-video models used to involve having a person do a cartwheel or really anything that required putting them in a non‑upright orientation.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#96

Earlier quoted context omitted.

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)

Just like there are still plays even though movies overtook them as the main form of entertainment with acting, so too will AI generation overtake movies with real people. It's simply cheaper and more freeform creatively to use AI so expect that to be the future.

The fundamental difference between AI and all the previous advances like that is that people actually liked and wanted films, synchronized sound, color, CGI, etc. and queued down the block for them. Same thing with electronic music, people enjoy listening to it. Not really the same thing with AI, most of the praise is about the impact it will have on the production process, cost-effectiveness, etc., what actually comes out tends to take the back seat. From what we've seen it's pretty difficult getting people to like the output as well.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#97

Earlier quoted context omitted.

Just like there are still plays even though movies overtook them as the main form of entertainment with acting, so too will AI generation overtake movies with real people. It's simply cheaper and more freeform creatively to use AI so expect that to be the future.

The fundamental difference between AI and all the previous advances like that is that people actually liked and wanted films, synchronized sound, color, CGI, etc. and queued down the block for them. Same thing with electronic music, people enjoy listening to it. Not really the same thing with AI, most of the praise is about the impact it will have on the production process, cost-effectiveness, etc., what actually com…

You should read up on the history of each of those, they all had major protesters until everyone acclimated. So too for AI media in a decade or two. We already have people talking to their AI girl and boyfriends, it's not a big leap to think it'll be normalized.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#98
post #10

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!

"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...

And boy, will this thing make Disney mad. Least-censored model of any type I've ever seen from a major lab.

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#99

Earlier quoted context omitted.

The fundamental difference between AI and all the previous advances like that is that people actually liked and wanted films, synchronized sound, color, CGI, etc. and queued down the block for them. Same thing with electronic music, people enjoy listening to it. Not really the same thing with AI, most of the praise is about the impact it will have on the production process, cost-effectiveness, etc., what actually com…

You should read up on the history of each of those, they all had major protesters until everyone acclimated. So too for AI media in a decade or two. We already have people talking to their AI girl and boyfriends, it's not a big leap to think it'll be normalized.

of course they had critics, that's kind of what my point is addressing. but we didn't have to wait years for society to potentially acclimate to those previous advancements, they had an overwhelming proportion of fans on day one. and not sure what ai boy/girlfriends have to do with anything

Re: MiniMax H3 Day-0 Support in ComfyUI: Open Weights, Native Audio, and 2K Video

#100

Earlier quoted context omitted.

You should read up on the history of each of those, they all had major protesters until everyone acclimated. So too for AI media in a decade or two. We already have people talking to their AI girl and boyfriends, it's not a big leap to think it'll be normalized.

of course they had critics, that's kind of what my point is addressing. but we didn't have to wait years for society to potentially acclimate to those previous advancements, they had an overwhelming proportion of fans on day one. and not sure what ai boy/girlfriends have to do with anything

We did in fact have to wait years for them to be accepted, such as photography in the art world, as I said I suggest you read up more heavily on their history. I brought up AI girlfriends as an example of such normalization of AI already occuring. As well, even for AI slop there are fans, such as https://en.wikipedia.org/wiki/Fruit_Love_Island. Just because you or I aren't fans does not mean they do not exist or are unknown.
Post reply on HN