LoRA training of the https://huggingface.co/SG161222/Realistic_Vision_V6.0_B1_noVAE/tree/main in the kaggle notebooks with a scheduled run.
LoRA trained on CelebA-HQ dataset of first 1000 images. The dataset is taken from https://www.kaggle.com/datasets/kashyapkvh/mm-celeba-hq-dataset
Training duration is less than 40 minutes.
Training hardware 2x Google gpu
Training script is taken from diffuser repo: train_text_to_image_lora.py
Claude.ai is used for coding
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support