3.5: Base model NoobAI VPredA few fewer training images compared to 3.0对比3.0减少了一点训练图片3.0: Base model <a target="_blank" rel="ugc" href="https://civarchive.com/models/820208/obsession-illustrious-xl">Obsession (Illustrious-XL) - v-pred_v1.1 | Illustrious Checkpoint | Civitai</a>This is a NoobAI+Illustrious fusion model, and perhaps Lora is also generic这是一个NoobAI+Illustrious融合模型，或许Lora也具有通用性Tips: cleats,black cleats,green cleats,......提示词：cleats,black cleats,green cleats,......Detail is missing in panoramas, so try increasing the number of pixels or partially redrawing在全景图片中细节会缺失，可以试试提高像素数量或局部重绘2.0：Reduce and use single-style training assets, but rely on large models to still generate shoes of different colors.Trigger: sxzs \(shoes\),optional: red shoe,green shoe,1.0Old canvas sneakers This is a lora without convergence, but it still works.Change the color trigger word weight &gt; 1 example: (white qxz:1.2),weight:0.8-1

old cleats (shoes/sneakers)

减少训练素材，更换提示词

Files with SHA256: abbebbc94cb974dd2b4714e842a782d61aaf6b31eae435fb2c9849efb3b5398f