Stable Diffusion with Core ML on Apple Silicon
machinelearning.apple.com
Stable Diffusion with Core ML on Apple Silicon
1–10 of 184 posts
Re: Stable Diffusion with Core ML on Apple Silicon
#2Atila from Apple on the expected performance:
> For distilled StableDiffusion 2 which requires 1 to 4 iterations instead of 50, the same M2 device should generate an image in https://twitter.com/atiorh/status/1598399408160342039
Re: Stable Diffusion with Core ML on Apple Silicon
#3Re: Stable Diffusion with Core ML on Apple Silicon
#4Atila from Apple on the expected performance: > For distilled StableDiffusion 2 which requires 1 to 4 iterations instead of 50, the same M2 device should generate an image in https://twitter.com/atiorh/status/1598399408160342039
If you told me this was possible when I bought an M1 Pro less than a year ago, I wouldn’t believe you. This is insane.
Re: Stable Diffusion with Core ML on Apple Silicon
#5Atila from Apple on the expected performance: > For distilled StableDiffusion 2 which requires 1 to 4 iterations instead of 50, the same M2 device should generate an image in https://twitter.com/atiorh/status/1598399408160342039
Last nail in the coffin for DALL·E.
Re: Stable Diffusion with Core ML on Apple Silicon
#6Atila from Apple on the expected performance: > For distilled StableDiffusion 2 which requires 1 to 4 iterations instead of 50, the same M2 device should generate an image in https://twitter.com/atiorh/status/1598399408160342039
Last nail in the coffin for DALL·E.
yeah, finally we see the real openAI
Re: Stable Diffusion with Core ML on Apple Silicon
#7Atila from Apple on the expected performance: > For distilled StableDiffusion 2 which requires 1 to 4 iterations instead of 50, the same M2 device should generate an image in https://twitter.com/atiorh/status/1598399408160342039
i'm very ignorant here so forgive me but if it can generate images that fast can it be used to generate a video?
Re: Stable Diffusion with Core ML on Apple Silicon
#8Re: Stable Diffusion with Core ML on Apple Silicon
#9How does this compare with using the Hugging Face `diffusers` package with MPS acceleration through PyTorch Nightly? I was under the impression that that used CoreML under the hood as well to convert the models so they ran on the Neural Engine.
Re: Stable Diffusion with Core ML on Apple Silicon
#10How does this compare with using the Hugging Face `diffusers` package with MPS acceleration through PyTorch Nightly? I was under the impression that that used CoreML under the hood as well to convert the models so they ran on the Neural Engine.
It doesn't. MPS largely is on GPU. PyTorch's MPS implementation is incomplete a few weeks ago as well. This is about 3x faster.