ml-stable-diffusion
ml-stable-diffusion copied to clipboard
apple
Stable Diffusion with Core ML on Apple Silicon
I haven't been able to reproduce this myself, but I'm seeing some reports in Sentry. According to events in Sentry, it happens the moment the app moves from background to...
I was trying to run: > python -m python_coreml_stable_diffusion.torch2coreml --convert-unet --convert-text-encoder --convert-vae-decoder --convert-safety-checker -o And it wouldn't work as I got this error: File "/Users/..../opt/miniconda3/envs/coreml_stable_diffusion/lib/python3.8/site-packages/numpy/__init__.py", line 284, in __getattr__ raise...
When I run this, none of my test prompts come out looking anything at all like the demo images, they look terrible. Any ideas what might be going wrong? I...
My machine is a MacBook Air M1 with 16GB ram When using Stable Diffusion 2.1 from stabilityai, I get the following error spammed to console, seemingly with each step (but...
Will there be support for optional image width and height?
Hi, I've been compiling and using the project casually with the default model. I tried it with ``stabilityai/stable-diffusion-2`` today and all went well, until actual image generation with Swift. Here's...
It would be great if the python and Swift CLI tools could be run in a REPL/server mode for creating multiple image prompts. This way the model loading startup time...
I have `Apple Swift version 5.7.2`, `xcode-select version 2396.` and `Ventura 13.1` when I run `swift run StableDiffusionSample "a photo of an astronaut riding a horse on mars" --resource-path models/coreml-stable-diffusion-v1-4_original_compiled...
When trying to convert either the Decoder or the UNET with flexible shapes, coremltools fails. The first op to blame is the `group_norm` op. I found a related issue: [https://github.com/apple/coremltools/issues/1303](https://github.com/apple/coremltools/issues/1303)...
I've experienced multiple kernel panics trying to create a model with latent space of 64w-96h. I was able to do this without much problems when `--attention-implementation ORIGINAL` was used and...