Sign up free, get 10,000 credits

Starter credits added when you sign up.

LoRA utente

XL
Personaggio

Kazumi Schlierenzauer || Anime Style || Gokukoku no Brynhildr

#strega#Kazumi Schlierenzauer
Kazumi Schlierenzauer || Anime Style || Gokukoku no Brynhildr - AI Model cover image

Sign up free, get 10,000 credits

Starter credits added when you sign up.

Caricato su
12 set 2025, 15:21
Utilizzi
82
Recensioni
Eccellente  (1)
Parole d'ordine

Kazumi_Schlierenzauer, pink hair, blue eyes, short hair, hairband

Permessi
  • Allow image generation & sharing
  • Permettete agli utenti di scaricare il vostro modello
  • Usi commerciali

Recommended LoRAs

Descrizione

https://civitai.com/models/547049/kazumi-schlierenzauer-brynhildr-in-the-darkness TIPSPlease add 1girl , solo , adult , medium breasts before Kazumi_Schlierenzauer for best experience !! Use V12 https://civitai.com/models/827184/wai-nsfw-illustrious-sdxlUse Reference images for the negative prompts , cfg , sampler and LoRA strengthABOUT THE MODELThe 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://civitai.com/models/827184/wai-nsfw-illustrious-sdxl and other base models like Animij , Ghibli , Prefectious , etc [Default Base model is pathetic !!]TRAINING INFOThe 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 TIPSWhen 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 REQUESTI 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

Commenti

Artwork made by Kazumi Schlierenzauer || Anime Style || Gokukoku no Brynhildr