Type | |
Stats | 278 0 |
Reviews | (34) |
Published | Feb 22, 2024 |
Base Model | |
Training | Steps: 4,400 |
Trigger Words | Yennefer-512v1-4400 |
Hash | AutoV2 9BC667EB4D |
Pre Training
I gathered 30 images of Yennefer of Vengerburg. 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 gathered a mixture of game, netflix, and concept art images. 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 5K 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.