Furkan Gözükara
patreon
Started empirically experimenting for finding the best training hyper parameters for Stable Diffusion 1.5 based models
🕑 Added 2024-01-25 00:00:56 +0000 UTC- Using Kohya SS GUI as trainer script.
- Rented 8 GPU machine from RunPod and already doing 8 different trainings right now.
- If you have any input / feedback / suggestion let me know please.
Comments
Furkan Gözükara
I trained both on 768 and 1024. 768 works best and you can generate very good images at 1024. I will post full config. before testing OneTrainer. OneTrainer uses only 10300 MB VRAM on Windows
mypatreonemailacc
Can you share the base config you are using? Are you training at 512x512 resolution or higher?
Furkan Gözükara
optimizer, optimizer arguments, learning rate. still testing heavily
chriseppe
Very interesting. What are the main parameters you between the trainings? I.e. which training parameters in your opinion makes the biggest difference in quality?
