Pre Training

I gathered 16 HD images of Harry Styles. I am only using Birme to crop the HD photos instead of using Faceswap to align the faces. None of these images were full body, but some of them were zoomed out. 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 0.005:100:0.0025:250,0.001:500,0.0005:1000,0.00025 for my learning rate. I am going for 5K training steps total. I am using a batch size of 1 with Gradient Accumulation Steps set to 3. I am paying $0.465/hour for 1xRTX 4090. I am using 11.2 out of 24 GB of VRAM. The estimated time of completion is 2 hours. For the embedding I am using 4 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.