Warning: Highly experimental, does not work for a lot of things, often it's not the 1st person holding the item but the person in the picture, garbled hands, needs multiple tries etc (but it's my best attempt after many attempts). The Pony LoRA is considerably less capable than the Animagine LoRA.Trigger: <code>povhldg</code> &lt;item&gt;Helpful tag: <code>pov hands</code> (for Animagine), <code>pov holding</code> or <code>pov hand</code> (for Pony)Notes on Pony version The Pony LoRA works somewhat differently:<ul><li>The <code>povhldg</code> token has a weaker effect</li><li>Using <code>pov hands</code> may lead to multiple hands appearing, often focuses on hand holding</li><li><code>pov holding</code> seems to be a better supporting tag in Pony, but can lead to you using both hands</li><li>Update: Just found out that <code>pov hand</code> is better than <code>pov hands</code> for Pony</li><li>Sometimes the person is also holding the same item, <code>holding</code> in negatives may help</li><li>Unlike the Animagine LoRA, resizing it did not lead to improvements, so I left it at the original dim (8/4). But it also doesn't seem to hurt it (too much) so feel free to resize yourself</li></ul>The Pony LoRA was trained with a higher lr and more steps.

Files with SHA256: 8f3519d86062f8c454cca806024e35150a906dd2e591bb470f5836f4405d8aae