I’m trying to use sagemaker to run automatic with SDXL’s base model.
The Web UI just stays stuck on ‘Loading…’ (as shown in in the attached image), as soon as the page is up and till after the model is loaded (and beyond till infinity):
... Python 3.11.4 | packaged by conda-forge | (main, Jun 10 2023, 18:08:17) [GCC 12.2.0] Version: v1.5.0-RC-15-g1f26815d Commit hash: 1f26815dd3ea5a0b8c094854e47219aec866f28c Launching Web UI with arguments: --lowvram --no-progressbar-hiding --xformers --no-half-vae --share --styles-file /tmp/data/config/styles.csv Tag Autocomplete: Could not locate model-keyword extension, LORA/LYCO trigger word completion will be unavailable. Loading weights [1f69731261] from /home/studio-lab-user/content/stable-diffusion-webui/models/Stable-diffusion/sd_xl_base_0.9.safetensors Running on local URL: http://127.0.0.1:7860/ Creating model from config: /home/studio-lab-user/content/stable-diffusion-webui/repositories/generative-models/configs/inference/sd_xl_base.yaml Applying attention optimization: xformers... done. Model loaded in 121.1s (load weights from disk: 2.4s, create model: 14.3s, apply weights to model: 101.8s, apply half(): 0.1s, calculate empty prompt: 2.4s).
Does anyone know what might cause this?
I’ve tried removing any reference to the googlefont url, which seems to be the cause for some similar issues with Gradio, but that didn’t help.
It seems to have an issue loading the themes.css if I inspect the page that says Loading… in my browser (I’d give a screenshot but I can’t give more than one), could that cause it? Does anyone have a clue where I could:
-find a theme.css
-where in my automatic1111 folder do I place it?