Won-Kyu Park comments

Results 97 comments of


                                            Won-Kyu Park

Error when attempting to merge SDXL Inpaint .1 Beta model - Perhaps impossible? (RuntimeError: The size of tensor a (9) must match the size of tensor b (4) at non-singleton dimension 1)

now, inpainting model is supported by PR https://github.com/wkpark/sd-webui-model-mixer/pull/119

Error: 'NoneType' object has no attribute 'strip'

thank you for your reporting! Currently, auto merger does not manage/detect all possible conditions, that's why you've got the strange error.

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

when I come across a similar fatal error. "Extensions tab" -> "Apply and restart UI" will help for some cases. > Hey, first off congratulations on your extension. Having the...

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

Please reopen it or open a new issue if you encounter similar problems.

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13582 there are two issues exist. one is the issue already mentioned in this thread. ~~~diff diff --git a/modules/sd_models.py b/modules/sd_models.py index 0f1fb265..e466ef95 100644 --- a/modules/sd_models.py +++ b/modules/sd_models.py @@ -758,12 +758,13...

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

the main cause `NotImplementedError: Cannot copy out of meta tensor; no data!` error has been fixed by PR #29

Issue where model in merged but not save leads to "Cannot copy out of meta tensor; no data!" - persists through restart - had to disable app to continue

[AUTOMATIC1111/stable-diffusion-webui#13582](https://github.com/AUTOMATIC1111/stable-diffusion-webui/pull/13582) PR closed, but bugs have been fixed - the main cause of the bug was fixed by the author @AUTOMATIC1111 thanks @AUTOMATIC1111 and thanks to everyone for reporting bugs...

SDXL models trained w/ "One Trainer" are rejected w/ warning, "Warning model_a is SDNone but model_b is SDXL"

Are there any available/downloadable trained checkpoints?

SDXL models trained w/ "One Trainer" are rejected w/ warning, "Warning model_a is SDNone but model_b is SDXL"

> Here's one to test with: > > OT trained model export that reports "SDOne": https://drive.google.com/file/d/1OLHk8JhS9cRqGX_UcsPvosuAWZ6TEY22/view?usp=drive_link > > Oddly I'm not getting the popup warning this morning, so it's probably...

Previews don't match saved merge

thank your for your feedback! I've just tested using a SD1.5 model as follow: ~~~ ..(snip).. config hash = a0b03d5f552ec770ff274d77a1c86af6c46b198013c4e165ae5dd7505d3038a6 - mm_use [True, False, False, False] - model_a blessingMix_V1Fp16-vae.safetensors [267ad1beb5]...