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 performance is SOTA even compared to closed source models
If you want to play with this, as in really play, with over a dozen variant models with acceleration loras and a vibrant community, ya gotta check out:
Are there video generation benchmarks similar to how there are benchmarks for LLMs? Reason I ask is because with lots of these models you have to go through a long cycle to get them up and running before you see an output, and often they will break with basic tasks requiring physics, state, etc. Would love to see some comparison of models across basic things like that.
14 comments
[ 2.8 ms ] story [ 44.6 ms ] thread- 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 performance is SOTA even compared to closed source models
https://github.com/deepbeepmeep/Wan2GP
And the discord community: https://discord.gg/g7efUW9jGV
"Wan2GP" is AI video and images "for the GPU poor", get all this operating with as little as 6GB VRAM, Nvidia only.
- https://imgur.com/a/VeTn4Ej
- https://imgur.com/a/CujxVX3
Those were both Image to Video and then I upscaled them to 4k. I made the images using Flux Dev Krea.
Took about 3-4 minutes per video to generate and another 2-3 to upscale. Images took 20-40s to generate.