Последовательный мультяшный персонаж в Stable Diffusion | LoRa Training

In this video, I will try to make a consistent cartoon character by training a Lora. After Detailer: Kohya SS GUI: ::During Kohya SS GUI installation, you will need these steps to set: * In which compute environment are you running? – This machine * Which type of machine are you using? – No distributed training * Do you want to run your training on CPU only? – No * Do you wish to optimize your script with torch dynamo? – No * Do you want to use DeepSpeed? – No * What GPU(s) (by id) should be used for training on this machine? – All * Do you wish to use FP16 or BF16 (mixed precision)? – If you have a 30XX series GPU (or higher) – select BF16, otherwise select FP16. **LORA Training Config File: ::UpScaler:: Upscaler Model Database: 4x-UltraSharp Upscaler M