Type | |
Stats | 169 1,397 812 |
Reviews | (44) |
Published | Feb 27, 2025 |
Base Model | |
Training | Steps: 4,928 Epochs: 64 |
Usage Tips | Clip Skip: 1 Strength: 0.8 |
Trigger Words | sen tokugawa school uniform , purple eyes , brown hair , long hair master samurai outfit , purple kimono , purple eyes , brown hair , long hair fighting pose , weapon , holding weapon nude body , naked , breasts , nipples violet night dress mature body looking at viewer full body hand on hip +5 more |
Hash | AutoV2 7FCDCDACD8 |
RECOMMENDED PARAMETERS/TIPS
Lora weight = 0.6-0.9 Seems to work well for me , with 0.8 and 0.7 being best and some slight variations depending on the prompts
Works well with these 3 models as base models : WAI-NSFW-illustrious-SDXL V12.0 (https://civitai.com/models/827184/wai-nsfw-illustrious-sdxl) , Prefect IllustriousXL (https://civitai.com/models/1224788/prefect-illustrious-xl) , Animij V2 (https://civitai.com/models/1353314/animij) and Default illustrious-SDXL Base version .
For some reason cfg=3.5 with DPM++2M Keras seems to be doing quite nice , but I generally also use cfg=7-8 with DDIM/Euler-A . So please refer the sample images and decide based on your prompts (as they affect it a lot based on closeness to training data)
Try to keep the negative prompts minimal . In the positive prompts : First add some beautifiers/modifiers , then the general scene setting and finally the character specifict trigger words for enhanced experience ! (Eg : masterpiece, best quality, amazing quality, very aesthetic, absurdres, highres, anime coloring + indoors , classroom , windows open , 1girl , solo , standing , looking at viewer , one eye closed + Sen tokugawa , school uniform , brown hair , long hair , purple eyes , etc)
ABOUT THE MODEL
The model is excellent at generating beautiful anime-style images of Sen Tokugawa (A character from Hyakka Ryōran: Samurai Girls) . It can depict her in various poses, including standing and sitting, and 2-3 different primary outfits : School uniform , master samurai outfit and violet night dress . Mainly for SFW but also has a few NSFW training images since it is an ecchi anime lol !
TRAINING INFO
Training prompts were structured as tags, each consisting of 2-3 words, with 6-10 tags required for a detailed description. The model was trained for 65 epochs on a dataset of 77 images, using a Cosine Scheduler with repetition/cycles and the Prodigy Optimizer for fine-tuned results. Num_repeats = 4 , bs=4 , enabled bucket and shuffling tags .
INFERENCE TIPS
When using the model for inference, start by imagining a concept, pose, or activity, and describe it succinctly with short sentences. Negative prompts play a crucial role in refining outputs. While minute features can be added, their generation is not always guaranteed.
Feel free to experiment with other recommended resources to combine multiple pre-trained models, creating high-quality, diverse images. Use your creativity to craft beautiful and captivating images, and don’t forget to share your best outputs in a post to spread joy and gain appreciation!
Experiment with different settings such as Negative Prompts, Samplers, CFG scales, Steps, and Positive Prompts. Leverage already generated images and sample references to fine-tune your prompts, maximizing the model's potential. Have fun creating!
CREATOR REQUEST
I am more interested in seeing the diverse art-styles , poses and images that can be generated by my LoRA model using the creativity of the community . So please post your best images (following the below guide link) under model page to support creators as well . Thankyou . Enjoy ! Here are some Civitai Tips : https://civitai.com/articles/11156/how-to-improve-your-civitai-experience-v11