Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Wan – Open-source alternative to VEO 3

github.com

Post reply on HN
Print view View original

41–45 of 45 posts

Re: Wan – Open-source alternative to VEO 3

#41

Post by pkroll »

hypercube33 wrote: post #25
hirako2000 wrote: post #22

Earlier quoted context omitted.

It's hard to get an nvidia consumer having then less than 12GB of VRAM, not just these days. By GPU poor they didn't mean GPUless or GPU of the previous decade. It's on the readme that only Nvidia is supported.

I wish they'd state suggested or required hardware upfront. Also disappointing that I haven't seen anything target the new Ryzen AI chips that can do 96gb since they seem pretty capable. I'm not sure how much memory m4 pro on the apple side can be utilized for this but it seems like the typical machines are 48 or 64gb these days. Lot more bang for your buck than an Nvidia card on paper?

Well, they sort of do: they keep referring to the 4090, on their Github and primary promotional pages (https://wan.video/).

But really all the various video models really want an 80+ gig vram card, to run comfortably. The contortions the ComfyUI community goes through to get things running at a reasonable speed on the current, dinky-sized vram consumer cards, are impressive.

Re: Wan – Open-source alternative to VEO 3

#42

Post by giancarlostoro »

zakki wrote: post #40
giancarlostoro wrote: post #37

Earlier quoted context omitted.

That doesn't stop Mac / iPhone from using these models. I've build videos with Wan 2.2 on my wife's M4 Mac Mini w/ 24GB of RAM. It might take a little longer to render though ;)

Nice. Any reference for the installation?

Draw Things app in the appstore is free, open source and holds your hand.

Re: Wan – Open-source alternative to VEO 3

#43

Post by cubefox »

mandeepj wrote: post #20
cubefox wrote: post #9

Arguably most interesting facts about the new Wan 2.2 model: - they are now using a 27B MoE architecture (with two 14B experts, for low level and high level detail), which were usually only used for autoregressive LLMs rather than diffusion models - the smaller 5B model supports up to 720p24 video and runs on 24 GB of VRAM, e.g. an RTX 4090, a consumer graphics card - if their benchmarks are reliable, the model perfo…

> - the smaller 5B model supports up to 720p24 video and runs on 24 GB of VRAM, e.g. an RTX 4090, a consumer graphics card Seems like you can run it 2 Gpus each having 12 GB VRAM. At least, a breakdown on their GitHub page implied so.

That would be a lot cheaper than an RTX 4090.
Post reply on HN