ml-stable-diffusion VS tch-rs

Not sure how that got in here. Apple released CoreML Stable Diffusion library a little over a year ago [1]. Hugging Face released their version of the example app for the CoreML Stable Diffusion library [2].

The app should be able to run on iPhone 14 Pro, I believe the requirements is about 6-8Gb of RAM. And I was not able to run it on iPhone 13 Mini, because it has only 4Gb of RAM.

- [1] https://github.com/apple/ml-stable-diffusion

Where are you seeing a Stable Diffusion example? I'm familiar with Apple's CoreML Implementation of StableDiffusion, but is there something else in the SD world available for download now as part of MLX?

Other features and improvements to the repo https://github.com/apple/ml-stable-diffusion

M1! https://github.com/apple/ml-stable-diffusion

M2 MBA can run Stable Diffusion and LLaMa comfortably, which means generating your potential game/image asset locally. They're pretty much impractical in 7340.

Interestingly these are OpenCL kernels so in theory some of the optimizations might run out-of-the-box on CPUs.

It would be instructive to compare their speedups on the iPhone to the Apple CoreML implementation: https://github.com/apple/ml-stable-diffusion

Stable Diffusion runs great on my M1 Macs. The Draw Things app makes it really easy to run too. You also can’t disregard that Apple’s M chips actually have dedicated neural processing for ML/AI. This actual makes a Mac more affordable in this category because you don’t need to purchase a beefy graphics card. Not to mention that Apple has even optimized their software specifically for Stable Diffusion (related GitHub). Draw Things can take advantage of this. There’s a few guides to running the web UI on M1 too. I prefer the Draw Things app because of how easy it is to use, but the web UI is also nice because of all of the plugins and workflows that the community has built over time.

LINKS: ml-stable-diffusion: https://github.com/apple/ml-stable-diffusion Diffusers (HuggingFace Mac App): https://apps.apple.com/app/diffusers/id1666309574?mt=12

So, is Stable Diffusion working finally on TPU or not? DiffusionBee uses GPU and running this https://github.com/apple/ml-stable-diffusion with CPU_AND_NE just segfaults

I wanted to do something like this but then I would miss on proper CUDA acceleration and lose performance compared to using torchlib.

I wrote a forgettable llama implementation for https://github.com/LaurentMazare/tch-rs (pytorch's torchlib rust binding).

I first encountered OCaml's PyTorch bindings because apparently they generate a C wrapper around PyTorch's C++ API, and Rust's PyTorch bindings use OCaml's C wrapper. See: https://github.com/LaurentMazare/tch-rs

You could try looking at the min-GPT example of tch-rs. I'd also strongly suggest watching Karpathy's video to understand what's going on.

If you pefer to see it in code there's a succint gpt implementation here https://github.com/LaurentMazare/tch-rs/blob/main/examples/m...

Rust is fully compatible w/ C bindings, so even Python libraries written in C can be easily set up to work in Rust (and have been). For example, see PyTorch Rust bindings, which actually works faster than in Python because all of the glue code around the C++ API is in Rust instead of Python.

Pytorch

I have looked into this a bit and found some crates which help in loading torchscript models called tch-rs