Teriks

See also this line https://github.com/huggingface/diffusers/blob/cf6e0407e051467b480830d3ed97d2873b5019d3/src/diffusers/loaders/textual_inversion.py#L44 Here is code which tries to describe the problem ```python from diffusers import StableDiffusionPipeline import torch model_id = "runwayml/stable-diffusion-v1-5" pipe = StableDiffusionPipeline.from_pretrained(model_id, torch_dtype=torch.float16).to("cuda") # How...

Width = 720 results in a different exception ``` Traceback (most recent call last): File "REDACT\test.py", line 30, in decoder_output = decoder( ^^^^^^^^ File "REDACT\venv\Lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context return...

> @yiyixuxu , > > Shouldn't a simple check below suffice ? > > `sigmas = torch.from_numpy(sigmas).to(dtype=torch.float32, device=device) if not isinstance(sigmas, torch.Tensor) else sigmas ` > > I just did...

This indeed affects every page and all g-code is generated with this error from my mobile browser

This is caused by not providing an explicit value for X/Y offset under bed dimensions. I had a value there and I had removed it entirely guessing it would default...

as of `0.29.2` it seems that image alignments of `128` are possible.