31–40 of 45 posts
Wan2.1 was great, but Wan2.2 is really awesome! Here's some samples I made locally with my 5090: - 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.
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 27B "MoE" are not the MoE commonly referred to in LLM world. It is not MoE on FFN layers. It simply means two different models used for different denoising timestep ranges (exactly the same as SDXL-Base / SDXL-Refiner). Calling it MoE is not technically wrong. But claiming "which were usually only used for autoregressive LLMs rather than diffusion models" is just wrong (not to mention HiDream I1 is a model actually incorporated MoE layers (in FFN layer) and is a diffusion model).
- The A14B models can run on 24GiB VRAM too, with CPU offloading and quantization.
- Yes, it is SotA even including some closed source models.
Earlier quoted context omitted.
https://en.wikipedia.org/wiki/Wide_area_network
I'm familiar with that, but would people really confuse a video generation model for a type of computer networks?
But, I guess sometimes you use a plane to build a plane while the material is aligned to a particular plane.
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: 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.
If having only 6GB VRAM is GPU poor then I must be GPU destitute.
Earlier quoted context omitted.
If having only 6GB VRAM is GPU poor then I must be GPU destitute.
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.
Wan2.1 was great, but Wan2.2 is really awesome! Here's some samples I made locally with my 5090: - 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.
What did you use to upscale them?
Quick, someone make a UI for this and call it Obi.
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.
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 ;)