Request: Add Metal GPU Apple Silicon Support

[ronangrant]

It would be fantastic to see support for Metal GPU on Apple Silicon in Wan2.1. This enhancement could significantly improve performance for users on macOS devices. This would involve:

• Replacing CUDA device initialization with MPS (e.g., torch.device("mps" if torch.backends.mps.is_available() else "cpu")).
• Adjusting precision from float64 to float32 in areas like sinusoidal embeddings and rotary encodings.
• Handling random generation by creating tensors on CPU before moving them to MPS.
• Replacing CUDA-specific calls (e.g., torch.cuda.empty_cache(), torch.cuda.amp.autocast) with conditional alternatives.
• Adding a compatibility layer during model loading for device differences.

I’m willing to help contribute to this effort and collaborate with anyone interested in making this happen.

[bakhti-ai]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

[ronangrant]

You rock! Really appreciate your contribution!

[FurkanGozukara]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

i cant imagine speed :D what are the step speeds for 1.3b 480p and 14b 720p?

[bakhti-ai]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

i cant imagine speed :D what are the step speeds for 1.3b 480p and 14b 720p?

I haven't tested 14b 720p locally and not going to :D
I tried 1.3b, 480p, frame_num 8 and I think it took around 10mins to generate the video so 1min per step I guess

[bakhti-ai]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

i cant imagine speed :D what are the step speeds for 1.3b 480p and 14b 720p?

I haven't tested 14b 720p locally and not going to :D I tried 1.3b, 480p, frame_num 8 and I think it took around 10mins to generate the video so 1min per step I guess

Then I increased frame_num to 24 to generate a little longer video, then waited around 1,5 hours but it was only 20% I just stopped it there

[Fmstrat]

@Runtrons out of curiousity, why was this closed if #69 hasn't been completed/merged?

[buzsh]

Also wondering this, especially considering the new M3 Ultra

[infinitebliss1111]

also interested in mac optimised wan

[rajsync]

Any update on this?

[rajsync]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

Hi, tried your fork on my Apple M4 Pro video coes out blurry.

[bakhti-ai]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

Hi, tried your fork on my Apple M4 Pro video coes out blurry.

Hi, thanks for trying out my fork. Could you share more information on the options you gave it like frame_num, size etc.? And if there were any errors or warnings

[joostwestra]

Hi there, I forked and adjusted the repo to make it work on my macbook m1 pro. After adjustments it worked on macos. I opened a PR for this original repo as well. You can check it out here #69

Hi, tried your fork on my Apple M4 Pro video coes out blurry.

Try to change the sampler in ComfyUI to Euler, scheduler normal