README.md

---
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
widget:
- text: >-
    score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,
    Japanese  girl, floral kimono, shoulders tattoo, large back tattoo,  exposed
    shoulders, from behind, beautiful face, thick eyelashes, glossy eyes, black
    hair, cute smile, dark eyeshadow, floral decoration in hair, falling petals,
    beautifully backlit, wide shot, source_photo, realistic,
    <lora:glowneon_xl_v1:0.6>   <lora:Expressive_H:.8>
    <lora:43stl1ght1ngXLP2:0.5> 43stl1ght1ng,, volumetric lighting, depth of
    field, cinematic
  parameters:
    negative_prompt: >-
      greyscale, monochrome, source_pony, source_furry,  jpeg artifacts, 
      blurry, drawing, sketch, desaturated, artist name, signature,
  output:
    url: images/01841-1294712139.jpeg
- text: >-
    score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up,  red
    linework around the character, black background, smoke, red lines,
    spotlight, gold trim, symmetric rings, curvy, sexy, full body, shapely body,
    long blonde Hair, voluminous bun, black slingshot swimsuit, black blindfold,
    off shoulder, seductive pose, sensual lips, blindfold, simple background,
    natural breasts, perfect anatomy, flirting, mid parted hair, kneeling,
    suggestive pose, kinky,, volumetric lighting, depth of field, cinematic
  parameters:
    negative_prompt: >-
      greyscale, monochrome, source_pony, source_furry,  jpeg artifacts, 
      blurry, drawing, sketch, desaturated, artist name, signature,
  output:
    url: images/01843-1608674701.jpeg
base_model: LyliaEngine/Pony_Diffusion_V6_XL
instance_prompt: None
license: cdla-permissive-2.0
---
# vividpdxl_v11VAE

<Gallery />

## Model description 

VividPDXL Real (Near photorealism)
Why use this? It has decent color, skin texture and eye quality for a pony model, and can achieve photorealism.

NO UNNECESSARILY LONG NEGATIVE PROMPTS, MOST OF THE TIME THEY HURT RATHER THAN HELP!!!

    My usual visual tags are volumetric lighting, depth of field, cinematic, vibrant, shadows, detailed but these may force realistic images even if you are trying to do a different style.

    Use source_photo and Realistic tags to help get realistic images.

    Make sure to keep CFG around 7 and Sampling Steps around 30.

    Always use score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up you can remove the 4,5 and 6 one and you likely wont have any issues.

    score_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, just describe what you want, tag1, tag2

    Recommended Negatives: artist name, signature, only add more if you want to avoid things appearing in your generation like styles or objects&#x2F;people. You don&#39;t need to use tons of random negatives like deformed fingers I highly doubt they work.

    Use source_anime, source_photo, source_3d, etc.. to force or avoid certain styles. You won&#39;t see the style change that much but it can help.

    If you really want styles other than photorealism, you can try, but its not guaranteed. Try using words like style of &quot;stylehere&quot;, while putting source_photo, realistic in the negative prompt as well as describing elements of that style. Certain visual positive prompts can also force a realistic style as well, so try experimenting.

        If you go through the gallery below and look at badassdragoon2&#39;s images, you may find some examples of different styles you can use. Set 1, Set 2, Set 3, Set 4, Set 5, Set 6, Set 7, Set 8, and Set 9.

Check out this extension(tagcomplete) for automatic111 users to help with finding tags for pony models.

Also use danbooru to help find tags, it has a tag count to show you how popular certain tags are.
VividPDXL V1.1 (2.5d realistic style)
Why use this? This version produces a more 2.5d like style compared to REAL.

A slight update over 1.0 improving color slightly, and detail.

My usual settings for pony models are as follows:

Res: 1024x1024

Sampler: DPM++ 2M Karras (DPM++SDE Karras, DPM++ 3M SDE Karras are all excellent as well)

    Euler for lower detail images.

Steps: 30

CFG: 7

Hires Denoising: .3 - .4

## Source

https://civitai.com/models/381088?modelVersionId=438202

## Credit

https://civitai.com/user/insertusername

## Trigger words

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


## Download model

Weights for this model are available in Safetensors format.

[Download](/LyliaEngine/vividpdxl_v11VAE/tree/main) them in the Files & versions tab.