VLR_Project---Fine-Tuning-LLMs-for-Diffusion

Load data in Images folder with kaggle competitions download -c h-and-m-personalized-fashion-recommendations, then move Images to that folder

To load weights correctly, need: torch=2.1.0 torchvision=0.16.0 transformers=4.40.0

Name		Name	Last commit message	Last commit date
Latest commit History 31 Commits
Diffusion		Diffusion
LLM		LLM
Results		Results
Tokenizer		Tokenizer
VisionEncoder		VisionEncoder
__pycache__		__pycache__
data		data
full_train		full_train
segmentation		segmentation
stable-diffusion-2-1-unclip		stable-diffusion-2-1-unclip
.gitignore		.gitignore
LICENSE		LICENSE
README.md		README.md
custom_clip.py		custom_clip.py
full_train.py		full_train.py
full_train_fashion.py		full_train_fashion.py
generated_image.png		generated_image.png
inference.ipynb		inference.ipynb
inference.py		inference.py
llm.py		llm.py
load_data.py		load_data.py
mapping.py		mapping.py
new_fashion_clip.py		new_fashion_clip.py
requirements.txt		requirements.txt
stablediffusion.py		stablediffusion.py
test.png		test.png
test2.png		test2.png
vision_encoder.py		vision_encoder.py

Provide feedback