[perfopt]

How does this work? When I run it on a machine with a GPU (pytorch, CUDA etc installed) I still see it downloading files for each prompt. Is the image being generated on the cloud somewhere or on my local machine? Why the downloads?

[bryced]

Shouldn't be downloads per prompt. Processing happens on your machine. It does download models as needed. A network call per prompt would be a bug.

[perfopt]

OK. I noticed that the images are not accurate when I give my own descriptions. Not sure if this is a limitation of Stable Diffusion. For example, for the text "cat and mouse samurai fight in a forest, watched by a porcupine" I got a cat and a mouse (with a cat's face and tail!!) in a forest sort of fighting. But no - porcupine

Thank you for creating this.

[bryced]

yes stable diffusion is not great about handling multiple ideas. New image models coming out soon though.

[perfopt]

I keep seeing this even when the prompt is unchanged

Downloading https://huggingface.co/runwayml/stable-diffusion-v1-5/resolv... from huggingface Loading model /home/hrishi/.cache/huggingface/hub/models--runwayml--stable-diffusion-v1-5/snapshots/889b629140e71758e1e0006e355c331a5744b4bf/v1-5-pruned-emaonly.ckpt onto cuda backend...

followed by a download

[bryced]

That is strange. I'm not sure what would cause that unless it was running in some ephemeral environment. What OS? Can you open a github issue with a screenshot?

[perfopt]

Ubuntu 22.04.1 LTS. I'll file a issue

[bryced]

Oh I see what you're saying. It's not actually downloading but there is a bug where it's not using the cache properly. will fix

[searchableguy]

Is there a way to pre-download all models? I want to create a docker image and cache the models.

Also any way configure the generated file path beyond directory or directly pipe image from the CLI?