README.md

---
tags:
  - text-to-image
  - stable-diffusion
  - lora
  - diffusers
  - template:sd-lora
widget:
- text: >-
    high quality, defined pupil, looking at viewer, rounded pupil, defined iris,
    (soft iris:1.2), torso shadow,
  parameters:
    negative_prompt: >-
      bad_anatomy, deformation, amputation, deformity, deformed_nipples,
      duplicated_torso,  deformed_torso, long_torso, large_torso,
      unproportioned_torso, (deformed_pussy:1.2), (deformed_hands:1.2), 
      unproportioned_eyes, unproportioned_head, small_head, duplicated_nose,
      big_nose, fusioned_clothes, fusioned_arms, undefined_limbs, divided_pussy,
      red_pussy, duplicated_pussy,  deformed_anus, deformed_pussy,
  output:
    url: images/icon_3.png
base_model: Linaqruf/animagine-xl-3.0
instance_prompt: id_kanata_konoe

---
# Kanata Konoe

<Gallery />

## Model description 

This model was trained to generate high quality images based on SIFAS cards.

To achieve better quality, you should be using hako-mikan&#39;s regional prompter, along with Latent Mode, which modifies the way Stable Diffusion isolates the LoRA resulting in a significant improvement.

## Trigger words

You should use `id_kanata_konoe` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/theidoldaily/kanata-konoe/tree/main) them in the Files & versions tab.