MODEL INFO

The model excels at generating visually stunning images of Aoi Yuzuki (a character from Araiya-san!: Ore to Aitsu ga Onnayu de!?) in diverse poses, such as standing or sitting, and is particularly adept at creating cute and endearing visuals. It is suited for both SFW images and NSFW in separate versions ! . Works well with these 3 models as base models : WAI-NSFW-illustrious-SDXL (https://civarchive.com/models/827184/wai-nsfw-illustrious-sdxl) ; Default illustrious-SDXL Base version and Animagine XL V3.1 (https://civarchive.com/models/260267/animagine-xl-v31)

TRAINING INFO

The model was trained for 52 epochs on a dataset of 48 images [SFW] and 35 epochs on 57 images [NSFW], using prompts structured as tags with 2-3 words each, requiring 8–12 tags for detailed descriptions. Training was conducted with num_repeats = 3, batch_size = 3, a 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.

• For generating content pertaining to each of the outifts use the appropriate tag

• 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