(Changes In Updated Version)<ul><li>New dataset and training that won't always put your character's hands on their face like before</li><li>Removal of trigger word, it tends to be much more consistent when there is no trigger word</li></ul>Sitting Across From concept for Pony &amp; Animagine 3.1 XLI found this concept was very hard to consistently generate in Pony &amp; Animagine consistently, so I made a LoRA to make it easier. Usually, these models generate with a side-view of the character. This is trained to generate a direct, frontal, eye-level view.Important: Be careful not to describe legs, pants, feet, shoes, etc... in the prompt, otherwise it doesn't really know what to do. Upper body / arms only.Trigger words: no triggers words! Just add the LoRA!Recommended words:<ul><li>table<ul><li>if you want the table included</li></ul></li><li>negative prompt: hands on own face<ul><li>if you dont want the model to frequently output with the character's hands on their face</li></ul></li></ul>

Sitting Across From - Concept

640251_training_data.zip

Files with SHA256: fe1e6366a1b61810df9476455544726961dff9c70c95b84ade16dd9c56d9c65a