atila comments

Results 159 comments of


                                            atila

Apple Silicon : macOS 14 - error: ANEProgramProcessRequestDirect()

Hi @criskb, couple of notes: - I am unsure what you are referring to by `--no-half`, could you please clarify? - Looks like you are using a webui which is...

Update CLI to use @main

Closing the PR due to inactivity. Please feel free to reopen if you think there is an error, thank you! 🙏

Loading lora weights in pipeline.py has no effect on the models.

Hello! - LoRA in Core ML is not implemented in the current version of this library. - You may fork and add non-Core ML components (e.g. PyTorch) if you desire...

CoreML sdxl-v1-base-palettized fails on deployment to iPhone with error E5RT: MILCompileForANE error: failed to compile ANE model using ANEF. Error=_ANECompiler : ANECCompile() FAILED (11)

This is related to #242 as `cpuAndNeuralEngine` is meant to be used with a `SPLIT_EINSUM` (or `SPLIT_EINSUM_V2`) model whereas the model you linked to is an `ORIGINAL` model which is...

Is this copyrighted and licensable work from APPL? Do you plan to open-source it eventually?

License is now MIT thanks to @msiracusa et al.

Inference with SDXL on Python

Hello! The Python pipeline is a proof-of-concept and it does not include the changes necessary to support SDXL variants. The error you mentioned could be due to various reasons ([FAQ...

Inference with SDXL on Python

Those specs are just fine, SDXL runs on my M1 with 16 GB RAM. The issue might be that other concurrent processes might be taking too much RAM. Just to...

iOS 16 Palettization + Varying Model Architecture Support

Hi! 1. The same WWDC video also talks about ahead-of-time (eager, at load time) vs. just-in-time (lazy, during execution) decompression which is the main difference between iOS16 and 17. You...

Can't specify ``--image xx`` (`image2image`)

Hey @ToddCool, could you please confirm that you have `VAEEncoder.mlmodelc` in your `--resource-path`? If not, you will need to run `--convert-vae-encoder` to generate it during the PyTorch to Core ML...