Tessa Fowler, pinup glamour model LoRa.Use trigger words 'Tessa Fowler', and optionally 'wearing glasses' to add her signature black frames. Try [red hair] or [red lipstick] to accent. Works well 0.7-.85 weight. LoRa is nsfw so add to negative prompt.See version for training details.

Tessa Fowler

First and final version. 53 images of no glasses, 43 images of glasses, ranging from tight chin-forehead crop, shoulders, to full body. Trained in WebUI 2.1.6 using <a target="_blank" rel="ugc" href="https://github.com/d8ahazard/sd_dreambooth_extension">Dreambooth extension</a> on SDv1.5.Training details:<ul><li>Steps per image: 100 (with several restarts)</li><li>Batch Size: 3, GA: 3</li><li>LR Sched: constant</li><li>Unet LR: 0.00002</li><li>Text LR: 0.000005</li><li>Regularization using 'sexywoman' <a target="_blank" rel="ugc" href="https://huggingface.co/datasets/ProGamerGov/StableDiffusion-v1-5-Regularization-Images/tree/main">images from HF</a>.</li><li>Max resolution 1024 using buckets.</li><li>Concepts using 'photo of &lt;trigger word&gt; woman'</li><li>Dim, Alpha 64</li></ul>

Files with SHA256: 74234c0e03521e9e1c579c2ffbd46e5db9a8cdff0ebd4d4b67d9d6c4c54cd43e