---
license: other
license_name: bespoke-lora-trained-license
license_link: https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Rent&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- anime
- character
- overlord

base_model: runwayml/stable-diffusion-v1-5
instance_prompt: shalltear bloodfallen
widget:
- text: 'shalltear bloodfallen, casual dress, blood pool, 1girl, red eyes, solo, dress'
  output:
    url: >-
      92717.jpeg
- text: 'shalltear bloodfallen, casual dress, 1girl, solo, red eyes, smile, dress, long hair'
  output:
    url: >-
      92736.jpeg
- text: 'shalltear bloodfallen, armor, lance, sky, solo, wings, weapon, day'
  output:
    url: >-
      92735.jpeg
- text: 'shalltear bloodfallen, disguise, 1girl, blonde hair, red eyes, long hair, dress, hat, hair over one eye, flower'
  output:
    url: >-
      92734.jpeg
- text: 'shalltear bloodfallen, 1girl, solo, long hair, red eyes, naked towel, towel, very long hair'
  output:
    url: >-
      92732.jpeg
- text: 'shalltear bloodfallen, casual dress, 1girl, solo, red eyes, dress, long hair'
  output:
    url: >-
      92731.jpeg
- text: 'shalltear bloodfallen, casual dress, 1girl, red eyes, blush, solo, open mouth, smile, fang'
  output:
    url: >-
      92729.jpeg
- text: 'shalltear bloodfallen, casual dress, blood pool, 1girl, red eyes, solo, dress'
  output:
    url: >-
      92728.jpeg
- text: 'shalltear bloodfallen, casual dress, blood pool, 1girl, red eyes, solo, dress'
  output:
    url: >-
      92727.jpeg
- text: 'shalltear bloodfallen, casual dress, blood pool, 1girl, red eyes, solo, dress'
  output:
    url: >-
      92726.jpeg

---

# Shalltear Bloodfallen Lora 

<Gallery />





## Model description

<p>This lora was trained on 10 epochs, 10 repeats, with a dataset of 207 hand-picked images of Shalltear Bloodfallen. It works best by lowering the UNet strength to 0.7-0.8.</p><p></p><p>The dataset was tagged using waifu diffusion tagger 1.4 v2 with a threshold of 0.85 and then manually tagged with these tags: <strong>shalltear bloodfallen</strong>, <strong>casual dress</strong> (images with the dress she normally wears), <strong>armor</strong> (wearing her red armor), <strong>lance</strong> (holding her Spuit Lance), <strong>blood pool</strong> (the magic that create an orb of blood from her victims, this lora can recreate it very well), <strong>disguise</strong> (in her disguise) and <strong>nsfw.</strong></p>

## Trigger words
You should use `shalltear bloodfallen`, `casual dress`, `armor`, `lance`, `blood pool`, `disguise`, `nsfw` to trigger the image generation.
    

## Download model

Weights for this model are available in Safetensors format.

[Download](/Shinku/shalltear-bloodfallen-lora/tree/main) them in the Files & versions tab.

## Use it with the [🧨 diffusers library](https://github.com/huggingface/diffusers)

```py
from diffusers import AutoPipelineForText2Image
import torch

pipeline = AutoPipelineForText2Image.from_pretrained('runwayml/stable-diffusion-v1-5', torch_dtype=torch.float16).to('cuda')
pipeline.load_lora_weights('Shinku/shalltear-bloodfallen-lora', weight_name='shalltear-000010.safetensors')
image = pipeline('shalltear bloodfallen, casual dress, blood pool, 1girl, red eyes, solo, dress').images[0]
```

For more details, including weighting, merging and fusing LoRAs, check the [documentation on loading LoRAs in diffusers](https://huggingface.co/docs/diffusers/main/en/using-diffusers/loading_adapters)