---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- text: >-
    flat colors, highly detailed, detailed eyes, detailed face, detailed skin,
    simple background, (colourful), (cute character:1.2),  (tsundere
    expression:1.2), (blush), (red hair:1.2), messy hair, twintails, (sharp
    eyes), pouty lips, 1girl, 25 years old, adult, from above, portrait,
    close-up, face focus, depth of field, looking at viewer, white shirt, purple
    cardigan, off shoulder, crossed arms, full body shot, dutch angle,
    downblouse, big breasts, bikini top, beach, soft pastel colors, detailed
    background, masterpiece, best quality, very aesthetic, newest, absurdres
  parameters:
    negative_prompt: >-
      low quality, worst quality, lowres, bad anatomy, deformed, censored, bad
      hand, watermark
  output:
    url: images/00182-1252310960.png
- text: >-
    1girl, blue eyes, black hair, huge breasts, katana, fighting stance, front
    view, looking at viewer, long katana, dark atmosphere, blank gaze, blood on
    katana, blood on steel, dripping blood, masterpiece, best quality, highly
    detailed, good quality, newest
  parameters:
    negative_prompt: >-
      bad quality, worst quality, lowres, censored, bad hands, watermark, simple
      background
  output:
    url: images/00155-4089661856.png
- text: >-
    toned body, perfect face, cosy theme, posing, ((dynamic angle, from above)),
    black hair, 1girl, ponytail, solo, pink tank top, white panties, eyelashes,
    blue eyes, huge breasts, sagging breasts, bursting breasts, light smile,
    looking at viewer, seductive look, aroused, sultry expression,looking down,
    flat tummy, midriff, thin waist, bubble butt, breasts squeezed together,
    bent over, masterpiece, best quality, amazing quality, ultra-detailed, high
    resolution
  parameters:
    negative_prompt: bad quality, low quality, bad hand, watermark
  output:
    url: images/00157-2397844143.png
base_model: LyliaEngine/ilustmix_v40
instance_prompt: None
license: cdla-permissive-2.0
---
# bismuthIllustrious_v20

<Gallery />

## Model description 

Version 2: Cranking up overall details and contrast. Colors look more vivid too. Needs further testing.

Version 1: Overall very decent prompt adherence and anatomy. Stylisticaly close to anime-semirealism. Some combinations of LORAs give very interesting results (you can find examples in the images).

Recommended setitings:

Sampling method: Euler a, DPM++ 2M, DPM++ 2M SDE, DPM++ 2S a, DPM2 a, DEIS

## Source

https://civitai.com/models/1359028?modelVersionId=1648080

## Credit

https://civitai.com/user/Axelros

## Trigger words

You should use `None` to trigger the image generation.


## Download model

Weights for this model are available in Safetensors format.

[Download](/LyliaEngine/bismuthIllustrious_v20/tree/main) them in the Files & versions tab.