ml-stable-diffusion
ml-stable-diffusion copied to clipboard
apple
Stable Diffusion with Core ML on Apple Silicon
The benchmarks only include inference latency, but the actual latency is much larger. For example, they say it takes 18 seconds on the 32c M1 Max, which I have validated....
I got the following error , anyone know why? when i run the generate cmd, i always got the following error, but i have set my xcode to version 14.1...
 issue: #56
issue: https://github.com/apple/ml-stable-diffusion/issues/52
When I use a "mantra" on the Internet, Python will report an error when save a picture because the prompt text is too long: prompt like this: ```text best quality,Amazing,Beautiful ...
Restricted to order 2, no dynamic thresholding. It achieves similar quality to PNDM in 25 steps (~10s in my Mac).
Otherwise the app may crash when attempting to use a random Int as a seed.
I saw that some people online were having trouble importing the models in their apps.
is it possible to use diffusers on macOS or iOS? or only on terminal with python? TIA
As far as I could see, the Swift CLI implementation currently doesn't support negative prompts. In the Python implementation, the negative prompt argument is tokenised, encoded into `uncond_embeddings`, and prepended...
