MORA: <a target="_blank" rel="ugc" href="https://civarchive.com/models/434763/all-characters-honkai-star-rail">All characters Honkai: Star Rail 星穹铁道全角色 - v2.0 | Stable Diffusion LoRA | Civitai</a>2024-6-22更新 Pony v3.0版本，数据集和v3.0版本一样，同样是2000图。2024-6-20更新 Animagine XL V3.1版本.使用2000张相关图片训练。基于 Animagine XL V3.1训练，加入了机甲紧身衣，以及机甲萨姆.原因：我40发抽到流萤了。TAG:<pre><code>firefly_\(honkai:_star_rail\)</code></pre><pre><code>firefly_\(ar-26710\)_\(honkai:_star_rail\),plugsuit</code></pre><pre><code>sam_\(honkai:_star_rail\)</code></pre><hr />PONY V2.0MORE:<a target="_blank" rel="ugc" href="https://civarchive.com/models/434763/all-characters-honkai-star-rail-40-character">All characters Honkai: Star Rail （40+ Character) 星穹铁道全角色 - v1.0 | Stable Diffusion LoRA | Civitai</a>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:<pre><code>firefly \(honkai: star rail\), 1girl, solo, , dress, long sleeves, hair ornament,,black hairband, medium breasts</code></pre>Trained 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: 1024*1024Recommended output resolution: 832*1216/1024*1280Discord : <a target="_blank" rel="ugc" href="https://discord.com/invite/CFpyHceF52">https://discord.com/invite/CFpyHceF52</a>Recommended dataset collection and processing tools: <a target="_blank" rel="ugc" href="https://github.com/deepghs/waifuc">https://github.com/deepghs/waifuc</a>Possibly the most user-friendly dataset processing UI currently in use： <a target="_blank" rel="ugc" href="https://github.com/Eugeoter/sd-dataset-">https://github.com/Eugeoter/sd-dataset-</a>3.0 :先更新一个单人版本，后面把机甲也塞进来~--感谢<a target="_blank" rel="ugc" href="https://civarchive.com/user/xianienie">@</a>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:<pre><code>(score_9,score_8_up,score_7_up,score_6_up,score_5_up,score_4_up</code></pre>Negative prompt:<pre><code>(score_4,score_5,score_3,score_2,score_1)</code></pre>SDXLV2 Version Update:<ol><li>The material has been expanded to 1289 images, allowing for more accurate feature description.</li><li>It supports the following three characters:<ul><li>Firefly (Honkai: Star Rail)</li><li>Stelle (Honkai: Star Rail)</li><li>Caelus (Honkai: Star Rail)</li></ul></li><li>It can generate more stable multi-person images.</li></ol>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<ul><li>Firefly (Honkai: Star Rail)</li></ul><ul><li>Stelle (Honkai: Star Rail)</li><li>Caelus (Honkai: Star Rail)</li></ul>3.可以生成较为稳定的多人图片<hr />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：700:100:100<hr />1.0(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: 1024*1024Recommended output resolution: 1024*1280Recommended model weight: 0.8~1

Star Rail 星穹铁道 Firefly  流萤 开拓者 Trailblazer   SD1.5/SDXL

firefly_pony.safetensors

Pony

Ponyv3.0

v3.0

Pony v2.0

solo

V2.0

SD15v1.0

v1.0

v0.9

Files with SHA256: b767edf734052080bb83b6bebde69c268308d210804cb30637ac39d0d57825fe