78Alpha

I managed to patch together a version of 4.5 that does this, has a long load time because of how I did it though. Names of files are kept in...

MacOS should be abandoned as a supported platform in the near future... Since it will be all ARM, making a port even harder to maintain.

Something I completely forgot since I haven't had to do it for a while, to package for Mac requires Mac. With the new ones on M1, there may not be...

I would assume it's the CUDA version it was built against being unable to properly interface with the new hardware. Similar issues were plaguing other tools like BoostMonocularDepth. You could...

Be prepared to pull your hair out if you get to it. Getting it setup on one machine is a chore, but getting it to work on someone else's is...

There was a pull for automatic that references the limits of TRT. https://github.com/AUTOMATIC1111/stable-diffusion-webui-tensorrt/pull/36 There is an upper limit of what it can do. As an example, if you have your...

Still has the aforementioned issues with being dynamic (size, maximums, minimums). But, it's at least an official implementation for A1111. Hopefully that means it's working now, and on windows. On...

It looks like it uses accelerate, so you could try `accelerate config` in the venv or environment and setup multi-gpu from there

image_adapter_v14.yaml is the one to rename `image_adapter_v14.yaml > t2iadapter_depth_sd15v2` for the SD15v2 version

> Can you try this commit [8c158f5](https://github.com/facebookincubator/AITemplate/commit/8c158f54278975a074f9cadf12982bcba259436d), it works well on my side. Tried out yours after the current master and all other versions failed to compile. This one throws...