Lora trained at Civitai using the Pony V6 model as a base, using the artistic style of bbmbbf.Always use the tag bbmbbf and by bbmbbf1) Another option is to make a Remix of images from the LoRA gallery so that the result comes out faster and closer to the author's style.2) This first version of LoRA only works on models based on the Pony V6 version, in the future I intend to create a 2.0 version based on the SD 1.5 model3) Don't forget to use tags related to the Pony modelscore_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,1) Modify the LoRA weight between 1.50 to 2.00 so that the results are as close to the style as possibleBelow is an initial configuration, but any other type of configuration is up to you:ModelPony Diffusion V6 XLAdvancedCFG Scale - 7.0 ~ 9.0Sampler - DDIM / Euler a / DPM++ 2M KarrasSteps - 24 ~ 50Clip Skip - 1 / 2VAE - nonePrompt (Positive)score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, gray background, bbmbbf, by bbmbbf, anthro, furry, wolf, solo, female, hair, punky clothings, dynamic pose, dynamic anglePrompt (Negative)zPDXL-neg, 3DAs this model is based on Pony Diffusion there's not much need to specify anything in the negative prompt, because the Pony model is very flexible, but I always leave the zPDXL-neg tag (https://civitai.com/models/332646/pony-pdxl-negative-embeddings).
