TIPS

• Please add 1girl , solo , adult , medium breasts before Kazumi_Schlierenzauer for best experience !! Use V12 https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl

• Use Reference images for the negative prompts , cfg , sampler and LoRA strength

ABOUT THE MODEL

The model excels at generating visually stunning images of Kazumi Schlierenzauer (a character from Gokukoku no Brynhildr) in a 5-6 outfits : 1) Uniform , 2) Pink dress , 3) Yellow Camisole , 4) Red sleeveless 5) Green bikini 6)Violet Camisole top , Each style can be customized with the appropriate tags . The model captures her in diverse poses, such as standing or sitting, and is particularly adept at creating cute and endearing visuals. Small amount of nudity/bikini/bathtowel pics can be generated . Primarily a SFW Model . Best used with https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl and other base models like Animij , Ghibli , Prefectious , etc [Default Base model is pathetic !!]

TRAINING INFO

The model was trained for 43 epochs on a dataset of 123 images, using prompts structured as tags with 2-3 words each, one big sentence tag for each , requiring 10-15 tags for detailed descriptions. Training was conducted with num_repeats = 4, batch_size = 4, using Cosine Scheduler, and the Prodigy Optimizer for fine-tuning. Key settings included Tag Shuffling and Enable Buckets enabled, Clip_Skip = 1, and Noise_Offset = 0.1. The best epoch model was selected towards the end of training to ensure optimal performance.

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. Sometimes even draft generates good images !

• For generating content pertaining to specific style use the appropriate tag as well.

• 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, LoRA alpha , 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