Pre Training

I gathered 26 images of Eric Draven from the movie The Crow. I am using both facial images only because his makeup is his most notable trait. None of the images were full body. 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 $0.461/hour for 1xRTX 4090. I am using 11.2 out of 24 GB of VRAM. The estimated time of completion is 1 hour. For the embedding I am using 5 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.