psychedelicious

I don't think we want to implement a separate frontend for uploading models in the UI. You can set an API key, though: https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/#model-marketplace-api-keys Does that address your use-case?

Yes, you can read from environment variables. There's an example here: https://invoke-ai.github.io/InvokeAI/features/CONFIGURATION/#environment-variables Uploading files would similarly require the API key, no? To clarify, handling for uploading files to whichever model...

Ohhhh - I misunderstood. That's much more approachable and a nice UX improvement. I think we'd be happy to review a PR to do this. @hipsterusername thoughts (see message just...

@RyanJDick @hipsterusername Isn't this the same as adding multiple IP Adapters with the face model in the linear UI?

Do you mean that the images written to disk are black, or that they display as black in the UI only? If they display as black in the UI, but...

Can you upload one of the images here? Maybe there are some clues in the image.

@Piioupiou Sorry to hear that! Is it every image it just some? Can you please copy and paste the output from your terminal, starting from "image generation requested" for an...

@Piioupiou Looks like you have 4GB VRAM. Is that accurate? What OS and video card?

At 4GB you are right on the edge of what our implementation needs (probably below it, I'm sorry I can't remember the exact memory characteristics at this point). When you...

@Piioupiou Sorry, I'm AFK and wasn't sure. The correct flag appears to be `--no-xformers`, from the help text in the error you provided. Can you try that?