Lucrecia from Counter:Side 카운터사이드 This model was trained on a single game cg and several AI generated images.<pre><code>Note:
This is a B-LoRA. Use the style LoRA to adjust the effect of game cg style.</code></pre>Prompts:-<ul><li>Trigger Words:</li></ul><pre><code>lucrecia_olis, 1girl, purple hair, hair over one eye, blue eyes</code></pre><ul><li>Main Outfit:</li></ul><pre><code>neck ribbon, cleavage, fur-trimmed cloak, see-through leotard, asymmetrical legwear

Optional:
circlet, mouth veil
single fingerless glove</code></pre><ul><li>Optional:</li></ul><pre><code>expressionless</code></pre><ul><li>Negative Prompts (optional):</li></ul><pre><code>circlet, mouth veil, single fingerless glove, staff, holding staff
simple background</code></pre>Weights Tested:<pre><code>Character LoRA: ~0.8-1
Style LoRA: ~0.5+ for a more accurate outfit
 ~1 for a more accurate game CG style

(Feel free to experiment with the weights.)</code></pre>Known Issues:<ul><li>The model may be a bit overtrained, as I prefer a more accurate outfit. Feel free to reduce the LoRA weights if needed.</li><li>You might need to increase the weight of certain hand poses, since the game CG has only one pose. </li></ul>Afterword: This is my first time working with a single image. I started by cropping it into various proportions and then used these to train a model. Afterwards, I generated some images with this model and cherrypicked those with different outfits and angles to reduce outfit bleeding. Finally, I trained a model with both these AI images (using a lower loss weight) and the original images. Hopefully some of you will like this model.

[PonyXL B-LoRA] Lucrecia | Counter:Side 카운터사이드 | 未來戰

The model was trained on Pony Diffusion V6 XL.

Files with SHA256: fdd6608533bdb421038edce03b690bde2cc45ff3322e5f5dbf9adec2e24cfda3