Lora is trained on Flux images.The LoRA model was created based on 30 images taken from publicly available sources on the Internet.LoRA was trained on the FLUX_Dev model.Works based on the Tonal Anime keywords.When added to a hint (comic illustration), LoRA draws an illustration.CFG scale: 3.5, experiment with values.Steps: 14-30, experiment with values.Weight: 0.4-1.5.Visible effects will start to appear at values ​​of 0.4+.Works great in the range (0.6-1.3), depending on your preference, experiment with weights up to 1.3. Experiment with values.Depending on the model, the Lora weight can be increased quite a bit.High-quality hints reduce the negative effect.

Files with SHA256: 3aa4d325798f9f4687c58a37c21c747a8ab294d6b742158f4f97a873a301a8a8