[Bug]: Doesn't generate images

[GabrielSancho]

Is there an existing issue for this?

• [X] I have searched the existing issues and checked the recent builds/commits

What happened?

Today i wanted to use SD with Automatic1111 but when i started to write my prompt, it didn't recognize the number of characters at all and couldn't create any image, not in txt2img nor img2img with any Model AND when i choose a model in the upper left corner it doesn't reload anything, its like it doesnt recognize the models i use for some reason

Steps to reproduce the problem

1. Go to Webui user Batch File
2. start the batch file
3. Run SD Automatic 1111 locally
4. Choose a Model
5. Hmmm why any model make the loading animation?
6. Hmm why in the prompt section doesnt count the text?
7. Cry

What should have happened?

Work normally

Sysinfo

I dont know how to put this

What browsers do you use to access the UI ?

No response

Console logs

venv "C:\AI\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug  1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)]
Version: v1.2.1
Commit hash: 89f9faa63388756314e8a1d96cf86bf5e0663045
Installing requirements

Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
2023-10-18 19:15:01,767 - ControlNet - INFO - ControlNet v1.1.312
ControlNet preprocessor location: C:\AI\stable-diffusion-webui\extensions\sd-webui-controlnet\annotator\downloads
2023-10-18 19:15:01,831 - ControlNet - INFO - ControlNet v1.1.312
Checkpoint revAnimated_v121Inp-inpainting.safetensors [8836c40038] not found; loading fallback dungeonsNWaifusNew_dungeonsNWaifus22.safetensors [249bc94ed2]
Loading weights [249bc94ed2] from C:\AI\stable-diffusion-webui\models\Stable-diffusion\dungeonsNWaifusNew_dungeonsNWaifus22.safetensors
*Deforum ControlNet support: enabled*
Creating model from config: C:\AI\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.
Startup time: 8.7s (import torch: 1.6s, import gradio: 1.1s, import ldm: 1.8s, other imports: 0.9s, load scripts: 1.2s, create ui: 1.9s, gradio launch: 0.2s).
Loading VAE weights specified in settings: C:\AI\stable-diffusion-webui\models\VAE\vae-ft-mse-840000-ema-pruned.ckpt
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Model loaded in 4.5s (load weights from disk: 0.6s, create model: 0.9s, apply weights to model: 0.8s, apply half(): 0.5s, load VAE: 0.2s, move model to device: 0.5s, load textual inversion embeddings: 0.9s).

Additional information

I dont know a lot about programming but i can provide more info if needed, pls help i love using IA

[PhreakHeaven]

@GabrielSancho

I just did a 'git pull' and the same thing happened. I'm using TortoiseGit and was able to revert to the previous version of '..\stable-diffusion-webui\modules\sd_models.py' to fix. GitHub won't let me attach a *.py file, so I zipped it up, if you would like to replace the newly borked one. Make a copy of your current 'sd_models.py' file first, just in case. sd_models.zip

[andupotorac]

This also happens to me with the latest version. Did you manage to figure out what was the issue?

[andupotorac]

Nevermind. I clicked the token number, deleted all text, wrote text again and now it finally generates images. Seems the issue is with the text field.