This comprehensive video tutorial equips you with the knowledge to train a high-quality real-life LoRA model. Discover step-by-step techniques for breathtaking AI portraits.
💡Looking for more? Access free posts, premium ComfyUI workflows, and personal support on my Patreon: https://patreon.com/myaiforce
Links:
- Running Stable Diffusion on RunPod: https://runpod.io?ref=jden1933
- Best Way to Use LoRA (LoRA + ADetailer Face Swap): https://youtu.be/-PULJo3SCJw
- Kohya Github Page: https://github.com/bmaltais/kohya_ss
- Training Base Model Download: https://huggingface.co/runwayml/stable-diffusion-v1-5/tree/main
- Online Cropping Tool: https://www.birme.net/?target_width=512&target_height=512
- How to Crop Training Images: https://youtu.be/Gf55-mGkFNc?t=337
- A1111's Tagger extension: https://github.com/toriato/stable-diffusion-webui-wd14-tagger
- How to Captioning: https://youtu.be/Gf55-mGkFNc?t=431
- Dataset Tag Editor: https://github.com/toshiaki1729/stable-diffusion-webui-dataset-tag-editor
- Optimizer Extra Arguments:
- When opting for DAdaptAdam, you'll need to configure it with specific arguments: --optimizer_args "decouple=True" "weight_decay=0.01" "betas=0.9,0.999"
- For Adafactor, the recommended arguments are: --optimizer_args "relative_step=True" "scale_parameter=True" "warmup_init=True"
Time Stamps
0:00 Intro
1:02 LoRA Training Flow
1:46 Principles Behind LoRA Training
3:46 LoRA Training Preparation
6:10 Understanding Core LoRA Training Parameters
13:36 Advanced LoRA Training Parameter Adjustments
18:44 Monitoring the Training Process
20:23 Finding the Best LoRA Model