Gartia

This would be nice. to have an OnStop. I am finding it annoying to deal with function calls, when i want to abort after a function call. But i getting...

Honestly that makes more sense that i think about it, because i'm sure in the future someone will probably want another type of padding as well like torus padding and...

It's mainly for generating textures, or repeating images such as panoramic ones. I have seen theres also better implementations such as wrapping the tensor like a torus, but would rather...

We could also have a single pad function instead of multiple using an enum or something. That way in case someone in the future needs to add more padding functionality...

Any LORA i've tried with sdxl atleast i don't have any base models downloaded. But you can try the [sdxl lightning 8 step lora](https://civitai.com/models/324115/sdxl-lightning-8step) I did a simple prompt of...

Wouldn't skipping n_dims of 0 skip scalars. I'm not extremely versed with machine learning, so i could be wrong

Yeah they are definitely being applied correctly i tested with the python version and got the same result as with cpp version, after that check was added its only a...

For testing purposes i'm using this setup: [Model](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) [Vae](https://huggingface.co/madebyollin/sdxl-vae-fp16-fix) [Lora](https://civitai.com/models/324115/sdxl-lightning-8step) `./sd.exe -v -m ./models/sd_xl_base_1.0.safetensors --vae './vae/sdxl.vae.safetensors' -s 1 -b 1 -W 1024 -H 1024 --lora-model-dir ./loras --cfg-scale 7 --steps 20...

That's really odd, im running on windows with cuda are you on a different OS/hardware maybe?