Version Update: SDXLTrained on the same dataset as the previous version: 16 images.My GPU is too weak for SDXL so I have to use TensorArt which ruins the generation data. These images were pure text2img -- there was no inpainting or edits. You can see the generation data and also use this model even if your GPU is bad at <a target="_blank" rel="ugc" href="https://tensor.art/models/665484360784460779">https://tensor.art/models/665484360784460779</a> <hr />Please checkout all my Pokemon Loras: <a target="_blank" rel="ugc" href="https://civarchive.com/collections/23688">https://civarchive.com/collections/23688</a><a target="_blank" rel="ugc" href="https://civarchive.com/tag/ghost%20pokemon">#Ghost Pokemon 👻</a> <a target="_blank" rel="ugc" href="https://civarchive.com/tag/poison%20pokemon">#Poison Pokemon ☠️</a><hr /><a target="_blank" rel="ugc" href="https://civarchive.com/articles/2397">Happy Halloween Month!🎃</a> I'm making Halloween Themed Loras: <a target="_blank" rel="ugc" href="https://civarchive.com/articles/2397">https://civarchive.com/articles/2397</a><hr />Trained on 16 imagesNetwork Dim: 32

Files with SHA256: 47355e080ce73c9963c6689c083bc99715d8d9260c761d8f591da18feafd87c4