Self-explanatory.Weight: 0.7-1.0Clothes can be easily changed. Style lora works easily.Anima Ver: Trained using 18 images. steps: 1260, epochs: 10, optimizerType: adamw8bit, Training parameter: lr: 0.0001, networkDim: 16, networkAlpha: 8, lrScheduler: cosine_with_restart, noiseOffset: 0.03IL Ver: Not really satisfy enough. If anyone can find or has the original <a target="_blank" rel="ugc" href="https://pixai.art/model/1888347135904521636">Aida-human-by Pan</a> file, which I assume it's probably originated from tensorart or a random guy, do use that because that one is a lot better.<h3 id="wallpaper">Wallpaper</h3><img src="https://image.civitai.com/xG1nkqKTMzGDvpLrqFT7WA/05507d1d-6687-4f42-856e-f5559171b113/original=true/05507d1d-6687-4f42-856e-f5559171b113.jpeg" />

Files with SHA256: 622face8df08ac63256fc43daca87777564ccf9c03f7bce08b293e4e48db991b