V2.0 is the recommended version! It's a total overhaul, making generating the "Looking at Self" pose much more consistent and reliable. Thanks to the community feedback re: v1.Tripled the dataset size with 1,998 training steps for better variety and accuracy.Intended for 2D, animé or Western illustration style images — supports furry, hetero, and yaoi prompts. Does not work well with realistic images. (While v2.0 is the better LoRA, v1.0 is still available to allow users to make comparisons, or to preserve nuances in case of user preference.) This LoRA reinforces the <code>looking at self</code> pose concept for Pony while keeping minimal impact on style.<ul><li>Enhances the downward head tilt, pulling the chin closer to the chest and revealing more of the crown.</li><li>Aligns the subject's eyes with their body when "looking down," avoiding the appearance of "looking away" pensively.</li><li>Adjusts pupils toward the nose rather than the center of the eye, for a focused and introspective look.</li></ul><ul><li>Tag: <code>looking at self</code></li></ul>Note: the LoRA adds a natural tendency for the subject to touch what they're looking at, such as a body part or clothing. Trained as a Bounty for user <a target="_blank" rel="ugc" href="https://civarchive.com/user/Deletetdyslexi">Deletetdyslexi</a>

Looking at Self

V2.0 is a total overhaul with a new dataset. It significantly enhances consistency and reliability in generating the "Looking at Self" pose, while keeping style impact to a minimum.<ul><li>Tripled the dataset size for better variety and accuracy.</li><li>Now works well with furry, hetero and yaoi prompts.</li><li>Fixes v1.0's inconsistencies for smoother results.</li><li>Mantains all prior features.</li></ul>

Files with SHA256: 6e857650ff6d280801800a58a8298be7dc3b2bd86ec490d4ea004f48a4886602