LoRAs are trained on images similar to Bara style, The dataset has NSFW so if you don't want to accidentally get such images add rating_safe in the prompt.Not only guys! These styles can still create girls, furries, ponies. But it works a little better on guysPreview generated without using ADetailerRecommended LoRA Strength: 0.5-0.7LoRAs have been trained on the Pony Diffusion V6 XL and I do not guarantee out good quality on other Pony Models<h2 id="heading-5">Tips</h2>You can add photo, realistic, 3D, CGI, render, source filmmaker, to the Negative prompt to make the image less realistic, You can also add lineart, flat color, to the prompt to make the image flatter.ㅤ<h3 id="heading-26">About OIS (One Image Style)</h3>These styles are trained on just one image, so they may not always be stable, but most of the time the styles are as stable as possible for LoRA trained on just one image<h3 id="heading-27">About ALT (Alternative)</h3>These versions of the styles may have less contrast and saturation or a different color.ㅤStyles are based partially or entirely on images created by the Neural Network (Artificial Intelligence)

OIS Bara Styles for Pony V6 XL

Repeats: 100Epoch: 20Image Count: 1Network Rank: 16Network Alpha: 8Batch size: 1Clip skip: 1Training steps: 2000Resolution: 792x1152Train Resolution: 1152x1152Model: ponyDiffusionV6XL_v6Captioning: WD14 Captioning (SmilingWolf/wd-swinv2-tagger-v3)Recommended LoRA Strength: 0.5-0.7

Files with SHA256: 8c27491b8dc686d5f9ff91a632ef540cd21913ecf9f51317f9514f0a05334cee