ABOUT THE MODEL

The model excels at generating visually stunning images of Makise Kurisu (a character from Steins;Gate) in a variety of styles, including: (1)Anime Style , (2)Game Style , (3)Mixed Style , (4) Maid Outfits . Each style can be customized with the appropriate tags (e.g., "anime style"). The model captures her in diverse poses, such as standing or sitting, and is particularly adept at creating cute and endearing visuals. Additionally, it has the capability to produce explicit content when prompted with the tag Rating:Explicit. 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 93 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 = 3, batch_size = 3, 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