ml-stable-diffusion
ml-stable-diffusion copied to clipboard
Stable Diffusion with Core ML on Apple Silicon
# pip3 install -r requirements.txt Collecting coremltools Using cached coremltools-6.1.tar.gz (882 kB) Preparing metadata (setup.py) ... done Collecting diffusers[torch] Using cached diffusers-0.11.1-py3-none-any.whl (524 kB) ERROR: Could not find a version...
V2?
Hi, curious if you plan to update this to V2?
I added ControlNet feature in model conversion and inference. **New Files** controlnet.py - ControlNet Model on PyTorch (Reference: https://github.com/huggingface/diffusers/pull/2407) - To optimize ControlNet on CoreML, there are some changes from...
I attempted to use this model for image-to-image: https://huggingface.co/coreml/coreml-Grapefruit/blob/main/original/512x768/grapefruit41_original_512x768.zip This model worked perfectly fine in text-to-image mode. However, when I passed a 512x768 image as the startingImage, I received an...
Some models like [Waifu Diffusion 1.4](https://huggingface.co/hakurei/waifu-diffusion) officially support prompts that are longer than 75 tokens. In Waifu Diffusion's case, It supports upto 225 token. Does this work with Apple's ml-stable-diffusion?
recently i downloaded the webui version in my mac, do i need to delete the webui version and just use this ?
My python skills are just not strong enough...anyone have any idea how (or if) ControlNet could be integrated into the CoreML conversion process? https://github.com/lllyasviel/ControlNet#controlnet-with-canny-edge
- [x] I agree to the terms outlined in CONTRIBUTING.md
OSError: Can't load config for 'stabilityai/stable-diffusion-2-1-base'. If you were trying to load it from 'https://huggingface.co/models', make sure you don't have a local directory with the same name. Otherwise, make sure...