ml-stable-diffusion
ml-stable-diffusion copied to clipboard
apple
Stable Diffusion with Core ML on Apple Silicon
When I run: ```swift let config = MLModelConfiguration() config.computeUnits = .all let pipeline try! StableDiffusionPipeline(resourcesAt: modelUrl, configuration: config) ``` I get the following error: ``` [espresso] [Espresso::handle_ex_plan] exception=ANECF error: failed...
It looks like the Scheduler only supports the PLMS sampler method. Is it possible to also support other samplers such as Euler?
filename should be truncated to 255 chars before saving. (in func imageName)
`python -m python_coreml_stable_diffusion.pipeline --prompt $prompt -i output-ml-packages -o ~/Desktop/ --compute-unit ALL --seed 93 --model-version runwayml/stable-diffusion-v1-5` The output : ``` INFO:__main__:Generated image has nsfw concept=False Traceback (most recent call last): File...
The reason is that depending on platform Int could be 64 bits or 32, also unsigned type. So when creating latents and parsing Int to UInt32, the system could throw...
Moved guidanceScale as a parameter for generateImages function. Also propagated this change for the performGuidance functions in order to use this parameter.
Will we be able to use this with Automatic1111?
FileNotFoundError: text_encoder CoreML model doesn't exist at /Users/seanfrohman/Documents/AI_MODELS/Stable_Diffusion_version_CompVis_stable-diffusion-v1-4_text_encoder.mlpackage So if I go ahead and install without using --model-version stabilityai/stable-diffusion-2-base It works fine during install, but then I get the error...
 Simply added a web UI to make ML Stable Diffusion easier to use. // The `seed` parameter used to reproduce the results was removed pr: https://github.com/apple/ml-stable-diffusion/pull/55
