Update dataset. Retrain the model using new craft.
Update dataset. Retrain the model using new craft.
Update dataset. New version is trained using new craft.
Update dataset. Fix the compatibility problem induced by VAE. Try to make the character more maternal.
Reduce dim to 1. The generating quality remains essentially unchanged.
A LoRA model of Kafka from Honkai: Star Rail. The trigger tag is 'star-kafka'. The key features are 'purple hair, pink eyes, sunglasses, hair between eyes, eyewear on head'. The 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) are recommended. 0.6 ~ 0.8 weights are good. The preview images are generated using 1.6 version (original) YesMix.
Some preview images are generated using 'Hires Fix' and upscaled using 'SD Upscale'. Thus, if you wanna generate the preview images, pls download the original preview images and analyze them using 'PNG INFO' in webui to get all generating information.
The maximum of generating resolution should not exceed 1024 theoretically, otherwise extra/deformed head/limbs will be waiting for you :). Try to use 'hires fix' to prevent this problem and help to generate higher-resolution images.
For 784mb VAEs (NovelAI, Anythingv3, Orangemix, Counterfeit) users, make sure add '--no-half-vae' in command line of webui to prevent generating black images. See voldy's log for the details of edit method. For high-performance GPU, make sure 'medvram' and 'lowvram' mode are disabled.