Closed jndietz closed 10 months ago
In https://github.com/kohya-ss/sd-scripts/blob/main/library/train_util.py#L1146
if torch.Size([4, 96, 168]) == latents.size():
print(image_info.absolute_path)
Something like that.
It looks like it's happening immediately so maybe it's something related to cache_latents and bucket_no_upscale.
One possible reason is there are two or more image files with same base name and different extension, for example "aaa.jpg" and "aaa.png". In this case, the latent cache file has been overwritten and has an illegal shape for one of the image.
Unfortunately, there is no checking in the script, so please verify your dataset.
You guys were right. Just renamed my files and the training completed. Thank you!
Looks like for SDXL training now exist problem with buckets. Because doesn't work with batch > 1 and when loading buckets ignores bucket_reso_steps.
I've been trying to train a LoRA, and I'm getting the following error:
I have a feeling one of the images is causing the issue. Is there a way to figure out which one?