<h3 id="another-lora-for-pony-xl!-liking-the-model-and-sharing-your-generations-is-much-appreciated-:)i'm-not-in-full-production-but-i'm-back!-ra42gak15">Another LoRA for Pony XL! 👍 Liking the model and sharing your generations is much appreciated :) I'm not in full production, but I'm back!</h3><ul><li>All models I make in the future will likely be male. Feel free to message me with any questions or potential requests. LoRA was trained on Pony. Prompting is just like any other, with the triggers: "LiesofPin, carlo, looking at viewer, black hair, short hair, freckles, 1boy, single mechanical arm, mechanical arms". If you're trying to recreate the exact character from the series, I recommend all of them; otherwise adjust as needed. For ease of generation, here is a list of common tags used in the training that you can use in both the Positive and the Negative:</li><li>"liesofpin, carlo, solo, looking at viewer, black hair, short hair, freckles, male focus, 1boy, realistic, blue eyes, upper body, brown hair, shirt, blurry background, blurry, belt, single mechanical arm, mechanical arms, white shirt, flower, collared shirt, weapon, candle, butterfly" Negatives that may be useful: "simple background, white background, cars" I like to use my <a rel="ugc" href="https://civarchive.com/models/474525/twinklingsquids-trusty-merge-or-melting-pot-pony-xl">MergifiedMales </a>model, but feel free to use any Pony model and share your results! Recommended weight is 0.5-0.95, but you can adjust as needed. The images generated were made with the following parameters a HighRes-Fix Script: Cfg: 3.0 - 8.0 Steps: 25 - 45 Sampler(s): dpmpp_3m_sde, Euler A, Scheduler: Karras, exponential Denoise: 1.00 Lora weight(s): 0.30-0.95 Happy generating!</li></ul>

Files with SHA256: b23aeda55fde9a36db89a238f6a5af24c84304bcf734528bc6cf8b2ad6991561