[x] I have searched the existing issues and checked the recent builds/commits
What happened?
I keep trying to follow along with Aitrepreneur's tutorial and how to create a Textual Inversion file but every time I get to preprocess this error appears
Steps to reproduce the problem
Go to stable diffusion train tab then the preprocess tab and after loading up 1.5 pruned file(I've tried both with the safetensors version and without) put in the directories you want to take/send the images to.
Press the Blip Checkmark and then press Preprocess.
Wait
What should have happened?
It should have started preprocessing and given me the processed images in the other folder.
Commit where the problem happens
22bcc7be
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
Other than the python path I haven't put anything else.
List of extensions
No this was a brand new install that I uninstalled and installed again only for the same problem to happen.
Console logs
venv "C:\Users\Jane\JaneSD\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)]
Commit hash: 22bcc7be428c94e9408f589966c2040187245d81
Installing requirements for Web UI
Launching Web UI with arguments:
No module 'xformers'. Proceeding without it.
Loading weights [e1441589a6] from C:\Users\Jane\JaneSD\stable-diffusion-webui\models\Stable-diffusion\v1-5-pruned.ckpt
Creating model from config: C:\Users\Jane\JaneSD\stable-diffusion-webui\configs\v1-inference.yaml
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
Applying cross attention optimization (Doggettx).
Textual inversion embeddings loaded(0):
Model loaded in 18.6s (load weights from disk: 5.8s, load config: 0.1s, create model: 1.6s, apply weights to model: 7.5s, apply half(): 0.9s, move model to device: 0.9s, load textual inversion embeddings: 1.7s).
Running on local URL: http://127.0.0.1:7860
To create a public link, set `share=True` in `launch()`.
Startup time: 25.4s (import torch: 1.7s, import gradio: 1.0s, import ldm: 0.6s, other imports: 0.9s, load scripts: 1.0s, load SD checkpoint: 19.1s, create ui: 0.8s, gradio launch: 0.2s).
Downloading: "https://storage.googleapis.com/sfr-vision-language-research/BLIP/models/model_base_caption_capfilt_large.pth" to C:\Users\Jane\JaneSD\stable-diffusion-webui\models\BLIP\model_base_caption_capfilt_large.pth
Error completing request
Arguments: ('task(rw6d8334cme9obz)', 'C:\\Users\\Jane\\Desktop\\birme-512x512', 'C:\\Users\\Jane\\Desktop\\birme-512x512\\Images', 512, 512, 'ignore', False, False, True, False, 0.5, 0.2, False, 0.9, 0.15, 0.5, False, False, 384, 768, 4096, 409600, 'Maximize area', 0.1) {}
Traceback (most recent call last):
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\call_queue.py", line 56, in f
res = list(func(*args, **kwargs))
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\textual_inversion\ui.py", line 19, in preprocess
modules.textual_inversion.preprocess.preprocess(*args)
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\textual_inversion\preprocess.py", line 17, in preprocess
shared.interrogator.load()
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\interrogate.py", line 123, in load
self.blip_model = self.load_blip_model()
File "C:\Users\Jane\JaneSD\stable-diffusion-webui\modules\interrogate.py", line 103, in load_blip_model
blip_model = models.blip.blip_decoder(pretrained=files[0], image_size=blip_image_eval_size, vit='base', med_config=os.path.join(paths.paths["BLIP"], "configs", "med_config.json"))
IndexError: list index out of range
Additional information
I did train the face on the dreamsharper model and inpainted it on a bunch of other outfits using the same model to get different pictures for the AI and then switched over to 1.5 for the training if that makes a difference.
shuishu
commented
1 year ago
Is there an existing issue for this?
What happened?
I keep trying to follow along with Aitrepreneur's tutorial and how to create a Textual Inversion file but every time I get to preprocess this error appears
Steps to reproduce the problem
What should have happened?
It should have started preprocessing and given me the processed images in the other folder.
Commit where the problem happens
22bcc7be
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of extensions
No this was a brand new install that I uninstalled and installed again only for the same problem to happen.
Console logs
Additional information
I did train the face on the dreamsharper model and inpainted it on a bunch of other outfits using the same model to get different pictures for the AI and then switched over to 1.5 for the training if that makes a difference.