<h1 id="marshmallow-fluff-sdxl">Marshmallow Fluff SDXL</h1>A LoRA for Stable Diffusion XL trained on the character marshmallow fluff, a furry female character.(Some sample images are at epoch 9. It performs way better in published final model.)Note: Sometimes watermarks/text might appear, try using a negative prompt against it.<h3 id="usage">Usage</h3>Add the LoRA to your prompt with your preferred weight (recommended: 0.7–1.0):marshmallow fluff, &lt;lora:marshmallow_fluff_sdxl:0.8&gt;Trigger wordsmarshmallow fluffRecommended settings<ul><li>Base model: Stable Diffusion XL 1.0</li><li>Resolution: 1024x1024</li><li>Sampler: DPM++ 2M Karras</li><li>CFG scale: 7–7.5</li><li>Steps: 25–30</li></ul>Training detailsTraining method: LoRAOptimizer: AdamW 8-bit

Files with SHA256: 32242e400c2cdaa348e78eda4fe9aab067f1ddc2bbfcdb6c55ee9bcfa2eedaa8