After spending the last 3 weeks and about ~100 attempts on trying to create this LoRA, I finally got a version I'm kinda happy with. Trained on 919 images. There is still a lot to improve but it can give good results. The sample images are raw outputs (txt2img + Hires. fix). I used the embeddings <a target="_blank" rel="ugc" href="https://civarchive.com/models/72437?modelVersionId=77169">UnrealisticDream, BadDream</a> (by <a target="_blank" rel="ugc" href="https://civarchive.com/user/Lykon">Lykon</a>) for some examples. All examples made with <a target="_blank" rel="ugc" href="https://civarchive.com/models/4201?modelVersionId=130072">RealisticVisionV51</a> (by <a target="_blank" rel="ugc" href="https://civarchive.com/user/SG_161222">SG_161222</a>). CFG Scale of 7 works fine.Main Keywords are:<ul><li>tongue out (749 trainers)</li><li>ahegao face (407 trainers)</li><li>drooling (99 trainers)</li><li>wet tongue out (77 trainers)</li><li>wide open mouth (44 trainers)</li></ul>Limitations:<ul><li>Subjects further away from the camera don't really work that well</li><li>Bias towards nose piercing (In a lot of training images)</li><li>Bias towards animal ears when using "ahegao face"</li><li>Keyword "wide open mouth" sometimes produces terrifying outputs</li><li>Keywords "tongue out to the side" and "licking lips" don't work (Not enough training images)</li><li>Might not work for males. Didn't test</li></ul>There would still be a lot to improve. I used a lot of medium quality (and some kinda low quality) images. But its hard to find more high quality images. Also I wasn't able to train above 512x512 since my RTX 3060 Ti couldn't handle more. That might could have improved quality also. I would love to make a SDXL Version but i'm too poor for the required hardware, haha.Note: The example images have the wrong LoRA name in the prompt. Tongues_V62-000012 was my original name before changing it to TonguesAndAhegaoV1.I appreciate your feedback!

Files with SHA256: 21257e7ded9abfe0d7dcc4aaa5b5707d16616016d98da1584d83372f4a4d7c29