ml-stable-diffusion
ml-stable-diffusion copied to clipboard
apple
Stable Diffusion with Core ML on Apple Silicon
I'm always receive following generated modules for: ``` swift run StableDiffusionSample "a photo of an astronaut riding a horse on mars" --seed 11 --output-path ./out/ --compute-units cpuAndGPU ``` 
I am seeing the following error when I try to run the image generation script. I am using MacOS Monterey Version 12.6.1 and my xcode version is 14.1 My protobuf...
I think we would need to convert the Encoder as well as the Decoder, looking into it but curious if anyone was already working on this
I was able to get `StableDiffusion` up and running in an app for macOS. Thanks for your incredible work, CoreML team! However the same setup does **not work** on my...
Correctly spell the words: Successfully facilitate getting pipeline overridden
% `flake8 . --count --select=E9,F63,F7,F82,Y --show-source --statistics` ``` ./python_coreml_stable_diffusion/pipeline.py:131:28: F821 undefined name 'List' uncond_tokens: List[str] ^ 1 F821 undefined name 'List' 1 ```
It takes 2 minutes to instantiate the pipeline on a M1. Seems to rule out use for all but the most curious early adapters. I spent an entire day on...
iOS 16.2 (20C5058d) ``` 2022-12-03 19:01:04.690255-0500 Hyperpaint[555:11322] [espresso] [Espresso::handle_ex_plan] exception=ANECF error: failed to load ANE model. Error=createProgramInstanceForModel:modelToken:qos:isPreCompiled:enablePowerSaving:statsMask:memoryPoolID:enableLateLatch:modelIdentityStr:error:: Program load failure (0x20004) 2022-12-03 19:01:04.702382-0500 Hyperpaint[555:11322] [coreml] Error plan build: -1. 2022-12-03...