Pre Training
I gathered 34 images of Paris Hilton. I am only using Birme to crop the HD photos instead of using Faceswap to align the faces. Some of the images were full body as I wanted to retain her face even when zoomed out. I also flipped the images horizontally to increase the number of images to train on. This should increase variety. These are 512x512 images instead of 1024x1024 images because I don’t have the specs to train a 1024x1024 model. I used Blip captioning to generate the filewords and edited each individually to reduce potential hallucinations.
Training
I used 0.005:100,0.0025:250,0.001:500,0.0005 for my learning rate. I am going for 10K training steps total. I am using a batch size of 1 with Gradient Accumulation Steps set to 3. I am running locally on a RTX 4090. I am using 12.5 out of 24 GB. The estimated time of completion is 2 hours. For the embedding I am using 8 vectors per token. I switched to SD 1.5 EMA Only model for training.
Things that I could have done better
I could have upscaled the images before extracting the faces so I could reduce blur.
Description
FAQ
Comments (2)
*** Error verifying pickled file from ...\stabledif\stable-diffusion-webui\embeddings\Paris_Hilton_512v1-10000.pt
*** The file may be malicious, so the program is not going to read it.
*** You can skip this check with --disable-safe-unpickle commandline argument.
***
Traceback (most recent call last):
File "...stabledif\stable-diffusion-webui\modules\safe.py", line 137, in load_with_extra
check_pt(filename, extra_handler)
File "...stabledif\stable-diffusion-webui\modules\safe.py", line 84, in check_pt
check_zip_filenames(filename, z.namelist())
File "...stabledif\stable-diffusion-webui\modules\safe.py", line 76, in check_zip_filenames
raise Exception(f"bad file inside {filename}: {name}")
Exception: bad file inside ...stabledif\stable-diffusion-webui\embeddings\Paris_Hilton_512v1-10000.pt: Paris_Hilton_512v1-10000/byteorder
---
*** Error loading embedding Paris_Hilton_512v1-10000.pt
Traceback (most recent call last):
File "...stabledif\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 236, in load_from_dir
self.load_from_file(fullfn, fn)
File "...stabledif\stable-diffusion-webui\modules\textual_inversion\textual_inversion.py", line 186, in load_from_file
if 'string_to_param' in data:
TypeError: argument of type 'NoneType' is not iterable
Getting the same error on your Marilyn Monroe as well
This is caused by not having the upgraded pytorch installed. I can't train on a GPU locally so I rent them and the image I was using didn't have it up to date. The embedding is harmless but for now --disable-safe-unpickle is my only solution. I will retrain all embeddings once I have resolved the issue.
I am tracking the issue here https://github.com/ai-dock/stable-diffusion-webui/issues/10
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.