ASastrange·Sep 10, 2025
The neural engine is used for the built-in LLM that does text summaries etc., just not third party LLMs.
And there's an official port of Stable Diffusion to it: https://github.com/apple/ml-stable-diffusion
In iPhone Airapple-aiml-research
ml-stable-diffusion
Python2022–2025
apple-aiml-research / ml-stable-diffusion
ml-stable-diffusion
Stable Diffusion with Core ML on Apple Silicon
17Distinct people
18Mentions
0Explicit recommenders
18KGitHub stars
What to know before exploring
What it is
Stable Diffusion with Core ML on Apple Silicon
GitHub
Where it is used
No documented product use was verified in the last source check.
What people are saying
No recommendation phrase was found in the indexed comments.
No classified warning is attached to this page. Read the discussions before treating silence as approval.
Also in these discussions
No other repository is repeatedly linked in the same discussions.
This week on Hacker News
Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 3:56:07 PM UTC.
No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.
Mentions over time
HN mentions by year18 dated mentions
Observed mentions: 2022-12-01 20:12:50 UTC to 2025-09-10 01:58:42 UTC.
Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.
View mention counts and date ranges
| Period | Start (UTC) | End (exclusive, UTC) | Mentions | Submissions | Comments |
|---|---|---|---|---|---|
| 2022 | 2022-01-01 00:00:00 UTC | 2023-01-01 00:00:00 UTC | 11 | 4 | 7 |
| 2023 | 2023-01-01 00:00:00 UTC | 2024-01-01 00:00:00 UTC | 4 | 0 | 4 |
| 2024 | 2024-01-01 00:00:00 UTC | 2025-01-01 00:00:00 UTC | 2 | 1 | 1 |
| 2025 | 2025-01-01 00:00:00 UTC | 2026-01-01 00:00:00 UTC | 1 | 0 | 1 |
What Hacker News says
18 sourcesShow HN: Offline sketch to image geneartor in a whiteboard
I'm excited to share my indie product, https://drawing.pics
In this post, I'll share all the technical details behind it.
So, what exactly is DrawingPics?
It's an image-to-image and sketch-to-image generator that runs in a whiteboard, allowing you to draw your draft directly on the canvas and easily generate the desired image.
How does it work from a technical perspective?
TLDR: Miniconda + Diffusers + Electron + Excalidraw
One of the most important aspects of creating this tool was finding a stable diffusion locally inference solution. There are many solutions available, such as https://github.com/leejet/stable-diffusion.cpp and https://github.com/apple/ml-stable-diffusion. I tested the C++ version, but the inference speed was very slow, and Metal GPU support still had issues (you can find relevant issues in their repo). Ultimately, I de
Read the rest
cided to use python to run it because PyTorch is mature and MPS support is well-established. And I chose Miniconda, because it can create a small, isolated Python environment to run the program.
The AI model should run in the background so that we can continuously produce images while you draw. We need to find an RPC method to enable communication between the Python process and Electron's Node.js process. The easiest way is to run a Python HTTP server, but the memory usage is too high. We need a more lightweight solution, so I used xmlrpc for memory efficiency, although there might be better alternatives that I'm unaware of. The AI inference part is handled by diffusers, which is great, but I had to apply some custom patches to make it work in this situation. This can be a bit challenging if you're not familiar with Python.
For the frontend, I initially used a low-level canvas library and tried to implement a drawing pad from scratch. However, it had too many details, so I chose a more mature option: Excalidraw. It's fantastic, with the only shortcoming being limited API support.
Finally, I combined all these technologies in Electron, ensuring they work smoothly on both the main process and the renderer process.
Ok, Is DrawingPics free to use?
80% of the project is free to use. I only charge a lifetime license for the effort I've put in, as I've spent 4 months on it and made numerous improvements based on user feedback. Currently, only Mac is supported. Windows support will be added later.
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
- [2] https://github.com/huggingface/swift-coreml-diffusers
In Show HN: Run Stable Diffusion Directly on iPhoneIt's also significantly slower than Apple M1, which is 2.2 iteration per second in iPad. Though, maybe it's not a fair comparison since Apple optimises heavily their library.
[0] https://github.com/apple/ml-stable-diffusion
In $95 AMD CPU Becomes 16GB GPU to Run AI SoftwareI've used Apple's port of Stable Diffusion on my Mac Studio with M1 Ultra and it worked flawlessly. I could even download models from Hugging Face and convert them to a CoreML model with little effort using Apple's conversion tool documented in their Stable Diffusion repo [1]. Some models on Hugging Face are already converted – I think anything tagged with CoreML.
[1] https://github.com/apple/ml-stable-diffusion
In Stability AI Launches Stable Diffusion XL 0.9Interestingly 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
In Speed Is All You Need: On-Device Acceleration of Large Diffusion ModelsSo, 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
In Transformer architecture optimized for Apple SiliconI've played around with many SD frameworks but I typically use: https://github.com/AUTOMATIC1111/stable-diffusion-webui since it has a lot of features and usually works well but it does have quirks/bugs that can be irritating. I use this webui on google colab (check "online services" in readme)
I have a M1 Max and have mostly avoided running SD on my machine since many SD implementations are built for windows or linux, supporting apple silicon had been less of a priority. Many of these frameworks will work on an M1 but i find using colab is simpler with similar performance.
However, since apple has released[1] Core-ML support SD models I have been trying some native apps like Mochi-diffusion[2] they seem to work well but are not yet as feature rich as the older webuis
1: https://github.com/apple/ml-stable-diffusion
2: https://github.com/g
Read the rest
Yes, it's using https://github.com/apple/ml-stable-diffusion
In Run Stable Diffusion natively on your MacApple has made a sample project available for Stable Diffusion that can run on both macOS and iOS.[1] The sample code is here.[2]
I'll concede that Stable Diffusion may or may not meet the threshold for SOTA but still think this is indicative of inference eventually becoming supported for any compelling LLM on consumer-grade hardware. The possibilities for creative tools are just too vast.
[1] https://machinelearning.apple.com/research/stable-diffusion-...
[2] https://github.com/apple/ml-stable-diffusion
In Deepmind’s AlphaCode conquers coding, performing as well as humans> Had to update my XCode to use the generated mlpackage files :/
I keep running into this, message is
RuntimeError: Error compiling model: "Error reading protobuf spec. validator error: The model supplied is of version 7, intended for a newer version of Xcode. This version of Xcode supports model version 6 or earlier.".
I upgraded XCode, tried re-installing the command line tools with various invocations of `sudo rm -rf /Library/Developer/CommandLineTools ; xcode-select --install` etc but still get the above message
(thanks in advance, in case you see this and reply)
edit: I see from https://github.com/apple/ml-stable-diffusion/issues/7 that somebody upgraded to macos 13.0.1 and that fixed the issue for them. I've put off upgrading to Ventura so far and don't want to upgrade just to mess around with stable diffusion on m1, if it can
Read the rest
be avoided.
>How come you always have to install some version of pytorch or tensor flow to run these ml models?
The repo is aimed at developers and has two parts. The first adapts the ML model to run on Apple Silicon (CPU, GPU, Neural Engine), and the second allows you to easily add Stable Diffusion functionality to your own app.
If you just want an end user app, those already exist, but now it will be easier to make ones that take advantage of Apple's dedicated ML hardware as well as the CPU and GPU.
>This repository comprises:
python_coreml_stable_diffusion, a Python package for converting PyTorch models to Core ML format and performing image generation with Hugging Face diffusers in Python
StableDiffusion, a Swift package that developers can add to their Xcode projects as a dependency to deploy image generation capabilities in their apps
Read the rest
. The Swift package relies on the Core ML model files generated by python_coreml_stable_diffusion
https://github.com/apple/ml-stable-diffusion
With the full 50 iterations it appears to be about 30s on M1.
They have some benchmarks on the github repo: https://github.com/apple/ml-stable-diffusion
For reference, previously I was getting about <3 minutes for 50 iterations on my Macbook Air M1. I haven't yet tried Apple's implementation but it looks like a huge improvement. It might take it from "possible" to "usable".
In Stable Diffusion with Core ML on Apple SiliconStable Diffusion with Core ML on Apple Silicon
3 points · Open discussionShowing the 15 most recent of 18 sources. Enable JavaScript to search and browse every indexed mention.