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://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl) , Prefect IllustriousXL (https://civarchive.com/models/1224788/prefect-illustrious-xl) , Animij V2 (https://civarchive.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://civarchive.com/articles/11156/how-to-improve-your-civitai-experience-v11