PONY V2.0MORE:All characters Honkai: Star Rail （40+ Character) 星穹铁道全角色 - v1.0 | Stable Diffusion LoRA | Civitai应粉丝要求更新，这个版本应该是目前最好的一个版本。此版本仅包含流萤一人TAG:firefly (honkai: star rail), 1girl, solo, , dress, long sleeves, hair ornament,,black hairband, medium breastsTrained using 746 imagesPlease choose the appropriate age rating based on your needs.Training model: PonyRecommend model: Pony Diffusion V6 XL/T-ponynai3/AutismMix SDXLTraining resolution: 10241024Recommended output resolution: 8321216/10241280Discord : https://discord.com/invite/CFpyHceF52Recommended dataset collection and processing tools: https://github.com/deepghs/waifucPossibly the most user-friendly dataset processing UI currently in use： https://github.com/Eugeoter/sd-dataset-3.0 :先更新一个单人版本，后面把机甲也塞进来~--感谢@xianienie 制作的动图TAG: firefly (honkai: star rail), 1girl, solo, , dress, long sleeves, hair ornament,,black hairband, medium breastsPony Version Update:prompt:(score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_upNegative prompt:(score_4,score_5,score_3,score_2,score_1)SDXLV2 Version Update:The material has been expanded to 1289 images, allowing for more accurate feature description.It supports the following three characters:Firefly (Honkai: Star Rail)Stelle (Honkai: Star Rail)Caelus (Honkai: Star Rail)It can generate more stable multi-person images.SDXLV2版本更新：1.素材扩充到1289张，可以更准确地描述特征2.支持以下三个角色Firefly (Honkai: Star Rail)Stelle (Honkai: Star Rail)Caelus (Honkai: Star Rail)3.可以生成较为稳定的多人图片SD15V1版本更新：训练模型：nai推理模型：MeinaMix建议权重：0.8~1建议开高清修复1、丝袜仍未还原2、尝试往4dim的模型塞三个角色，没有成功，可能为其他两位角色图片不够或者步数不足3、尝试出双人互动，未能成功4、训练集中，流萤、男开拓者、女开拓者的训练集比例为：700:100:1001.0(SDXL)版本更新TAG:firefly (honkai: star rail),1girl,solo,jacket,white dress,long sleeves,white flower,headband,1.洗掉了原先的建模画风，具有更好的泛化。但某种程度上，也是失去了“稳定”2.无头现象大幅度减少3.可以更好地双人互动了4.加入了 stelle (honkai: star rail) 和 caelus (honkai: star rail) 星穹主角，用于双人互动5.实际上是三人lora，三个角色都能单独使用6.丝袜还是没学好..0.9版本1.喂太多mmd了，lora自带了部分mmd画风2.被某角色厨指出丝袜并不还原，故暂定为0.9版本，后续优化3.好像“无头”现象出现的概率很高，原因未知，素材中没有去头图片TAG: firefly (honkai: star rail), 1girl, solo, white dress, long sleeves, blue thighhighs,jacketTraining model: Animagine XL V3Inference model: Animagine XL V3Training resolution: 10241024Recommended output resolution: 1024*1280Recommended model weight: 0.8~1
