<h3 id="heading-17">This is a Lora with a small training set, but its performance is beyond my expectation.</h3>v4 的权重请设置为0.6，clip skip：2v3 It is recommended that the clipping skip layer be 1However, we need to increase its weight when using it. It is recommended to be above 0.7, and 0.8-0.9 performs better!1. CLIP termination layer: 1/22. Weight range: 0.7 to 1, recommended: 0.83. Recommend matching large modelsFor unparalleled results, I highly recommend combining this Lora with the lbcrealistic model, which can be found in<h3 id="heading-18">Found at <a target="_blank" rel="ugc" href="https://civarchive.com/models/165986/lbcrealistic">https://civarchive.com/models/165986/lbcrealistic</a>.</h3>Or click on the recommended resources below.4. Seamless integration with other Lora modelsLora is designed to work seamlessly with other Lora models. When used with other Lora configurations, it can create significant synergies that improve overall performance. You can explore and try out different Lora combinations to find the one that best suits your unique fashion needs.Thank you for choosing My Lora and welcome your valuable feedback and suggestions. If you have any questions or need further assistance, please feel free to contact me.I have created a new TG channel, everyone is welcome to join and communicate: <a target="_blank" rel="ugc" href="https://t.me/+kNqrrSTSLoc1ZDhl">https://t.me/+kNqrrSTSLoc1ZDhl</a>

Exotic custom

建议：1. CLIP终止层：22.权重范围：0.3至0.9，推荐0.6 \权重越低泛用性越好！推荐使用“<a target="_blank" rel="ugc" href="https://www.liblib.ai/modelinfo/8c8f1c7f64d943ebb6b57833d5d042d2">lbc_Simple_简约</a>”大模型效果更佳。

Files with SHA256: 77440fdbe2961cab910b7dba85a99bec5b2ac0f38f9cbb339870b6747f37130c