> Are other open weight video models also this small?
Apples models are weights-available not open weights, and yes, WAN 2.1, as well as the 14B models, also has 1.3B models; WAN 2.2, as well as the 14B models, also has a 5B model (the WAN 2.2 VAE used by Starflow-V is specifically the one used with the 5B model.) and because the WAN models are largely actually open weights models (Apache 2.0 licensed) there are lots of downstream open-licensed derivatives.
> Can this run on a single consumer card?
Modern model runtimes like ComfyUI can run models that do not fit in VRAM on a single consumer card by swapping model layers between RAM and VRAM as needed; models bigger than this can run on single consumer cards.
No, using the WAN 2.2 VAE does not mean it is a WAN 2.2 edit.
> compressed to 7B.
No, if it was an edit of the WAN model that uses the 2.2 VAE, it would be expanded to 7B, not compressed (the 14B models of WAN 2.2 use the WAN 2.1 VAE, the WAN 2.2 VAE is used by the 5B WAN 2.2 model.)
> The more than 400,000 tech workers who have been laid off since 2022 are a clear reflection of wage suppression in the industry,
IMO, they are a clearer reflection of the fact that the industry has lots of jobs that are tied to remote future payoff and dependent on financing outside of operations, and that tighter money policies reduced the flow of investment into the broad industry (outside of the AI segment), cutting a lot of those jobs.
With $85/month service (AT&T unlimited premium with only a single line) and financing a $2,000 phone (The smaller storage version of the Galaxy Z Fold 7 at MSRP) over 18 months, you’d hit almost exactly that; you could so the same with a cheaper service and/or phone with some add-ons (e.g., while Apple Care is billed directly by Apple and so wouldn't be on a phone bill, insurance for non-Apple phones is often billed by carriers on phone bills.)
I'm sure Ol' John is no player when we compare how much investment funds have being pushing to buy homes. Around here, you can't even bid for a small apartment. They get sold to the folks before they start. Paying flat taxes on hundreds of properties doesnt make sense. They don't contribute to generate more jobs. They just replace the buyer and charge extra money that could have be reverted to other expenses that would create a healthier economy by diversity.
I wonder if the distribution of ages for home buyers is not a normal distribution and maybe the median and standard deviations might tell us something more here. Regardless it's concerning that the average and likely median age has shot up that much.
Well, since 1980, the median age in the population has also increased by about a decade, which is a significant (but not a majority) contributor to this.
A: and B: were both for floppies, dual floppy systems were around and common, both with and without hard disks, long before Zip disks existed, and Zip disks came around far too late (1994!) to influence the MS-DOS naming standard.
In English, typically em-dashes are set without spaces or with thin spaces when used to separate appositives/parentheticals (though that style isn't universal even in professional print, there are places that aet them open, and en-dashes set open can also be used in this role); when representating an interruption, they generally have no space before but frequently have space following. And other uses have other patterns.
Double hyphen is replaced in some software with an en-dash (and in those, a triple hyphen is often replaced with an em-dash), and in some with an em-dash; its usually used (other than as input to one of those pieces of software) in places where an em-dash would be appropriate, but in contexts where both an em-dash set closed and an en-dash set open might be used, it is often set open.
So, it’s not unambiguously s substitute for either is essentially its own punctuation mark used in ASCII-only environments with some influence from both the use of em-dashed and that of en-dashes in more formal environments.
OpenAI may be the worst, but I am pretty sure Anthropic is still bleeding money on AI, and I would expect a bunch of smaller dedicated AI firms are too; Google is the main firm with competitive commercial models at the high end across multiple domains that is funding AI efforts largely from its own operations (and even there, AI isn’t self sufficient, its just an internal rather than an external subsidy.)
Dario has said many times over that each model is profitable if viewed as a product that had development costs and operational costs just like any other product from any other business ever.
What that means, and whether it means much of anything at all depends on the assumed “useful life” of the model used to set the amortization period assumed for the development costs.
Sure, its smallish.
> Are other open weight video models also this small?
Apples models are weights-available not open weights, and yes, WAN 2.1, as well as the 14B models, also has 1.3B models; WAN 2.2, as well as the 14B models, also has a 5B model (the WAN 2.2 VAE used by Starflow-V is specifically the one used with the 5B model.) and because the WAN models are largely actually open weights models (Apache 2.0 licensed) there are lots of downstream open-licensed derivatives.
> Can this run on a single consumer card?
Modern model runtimes like ComfyUI can run models that do not fit in VRAM on a single consumer card by swapping model layers between RAM and VRAM as needed; models bigger than this can run on single consumer cards.
reply