⚔️ Nush from XTERNice Mommy is a NICE MOMMY <img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/68c36e5b-8641-4ddc-b1de-2ef47b839b33/original=true/68c36e5b-8641-4ddc-b1de-2ef47b839b33.jpeg" /><hr />🧠<h3 id="trained-with-anima-standalone-trainer-(https:github.comgazingstars123anima-standalone-trainer)">TRAINED with <a target="_blank" rel="ugc" href="https://github.com/gazingstars123/Anima-Standalone-Trainer">Anima-Standalone-Trainer (https://github.com/gazingstars123/Anima-Standalone-Trainer</a>)</h3><ul><li>DIT model below</li><li><a target="_blank" rel="ugc" href="https://civarchive.com/models/2414435/animax-anima-finetune-model">https://civarchive.com/models/2414435/animax-anima-finetune-model</a></li><li>animaxAnimaFinetune_v05.safetensors</li></ul><hr /><h3 id="training-info">⚙️ Training Info</h3><ul><li>Trainer: Trained with <a target="_blank" rel="ugc" href="https://github.com/gazingstars123/Anima-Standalone-Trainer">Anima-Standalone-Trainer</a> on an RTX 3080 10GB.</li><li>Base DiT Model: <a target="_blank" rel="ugc" href="https://civarchive.com/models/2414435/animax-anima-finetune-model">animaxAnimaFinetune_v05.safetensors</a></li><li>TAGS - nush, xter,</li></ul><hr /><hr /><h3 id="dataset-and-training-details-(no-lies-edition)-for-v1.">📦 Dataset &amp; Training Details (No Lies Edition) for V1.</h3><h1 id="(v2epoch-23-checkpoint-is-much-improved-go-for-that-one-for-more-detailed-nush-look)">(V2[epoch 2/3 checkpoint] is much improved - go for that one for more detailed Nush look)</h1>Keeping it 100% transparent about the dataset quality so you know exactly what to expect:<ul><li>V1.0 details / for v2.0 check changelog notes</li><li>Dataset Size: 141 images.</li><li>Quality &amp; Variety: Varied! The dataset contains a mix of black and white sketches, manga panels, a few screenshots from hentai, doujinshi illustrations, and fan art.</li><li>Cleanup: Manually edited to remove watermarks, text tags, or background characters from the images.</li><li>Tagging: Pre-processed and auto-tagged using Kohya_ss (WD14 captioner with Threshold 0.5 / General threshold 0.35 / Character threshold 0.35 confidence settings), then manually reviewed to add missing details and delete conflicting tags.</li></ul><hr />❤️ Share Your Generations!

Anima - Nush [XTER]

#### 📢 Release Notes: Version 1.0 (Public Initial Release)While this is the very first version being shared publicly on Civitai, under the hood, this is my V2 iteration of the model! I completely overhauled my internal test version to make sure it was ready for the community.---### 🔄 What's New &amp; Improved (Compared to my private V1 test):* Dataset Expansion: Expanded the dataset from 88 to 141 images for much better flexibility and concept coverage. (Full disclosure: her signature mole under the lip is still a bit inconsistent, but the overall likeness is way stronger!)* Deep Dataset Cleanup: Manually went through the entire dataset to meticulously remove text tags, intrusive watermarks, and background characters. * Refined Captions: Switched to an optimized Kohya_ss WD14 setup for base tagging and manually pruned the results to prevent concept bleeding.I'll probably try to crack that mole issue and force it to be 100% consistent for the next public update (V2), but for now, this is a massive upgrade. Enjoy!

Files with SHA256: 562eb771c97f80c924f77ba6a79274f9267e959eaa2169c36d409adf953b14ae