---
tags:
- text-to-image
- stable-diffusion
- diffusers
- template:sd-lora
- negative embedding
- embedding
- SDXL
widget:
- text: >-
    vampire bride,film photography aesthetic,the delicate texture of lace veil
    gently obscuring her face,long blonde hair,looking at viewer,eye eye
    contact,sapphire red eyes,choker,devil smile,dynamic composition,skin
    texture,from above,close-up,sharp focus,horror \(theme\),dutch angle,
  parameters:
    negative_prompt: DeepNegative_xl_v1
  output:
    url: >-
      images/xyz_grid-1082-2060917131-vampire bride,film photography
      aesthetic,the delicate texture of lace veil gently obscuring her face,long
      blonde hair,looking at.png
- text: >-
    (8K, best quality:1.2), (masterpiece:1.37), (photo, photorealistic:1.37),
    (ultrahigh-res), full body, walking pose, shot from front, slow motion,
    female paladin wearing the full body, (light silver armour:1.2),(ornately
    decorated armor), (insanely detailed, bloom:1.5), (highest quality,
    Alessandro Casagrande, Greg Rutkowski, Sally Mann, concept art, 4k),
    (analog:1.2), (high sharpness), (detailed pupils:1.1), detailed face and
    eyes, Masterpiece, best quality, (highly detailed photo:1.1), (long blonde
    Hair, ponytail,ecstatic:1.1), (young woman:1.1), sharp, (perfect body:1.1),
    realistic, real shadow, 3d, (temple background:1.2), (by Michelangelo),
    photographed by Canan EOS R6, 135mm, 1/1250s, f/2.8, ISO 400
  parameters:
    negative_prompt: DeepNegative_xl_v1
  output:
    url: >-
      images/xyz_grid-1086-3836843112-(8K, best quality_1.2),
      (masterpiece_1.37), (photo, photorealistic_1.37), (ultrahigh-res), full
      body, walking pose, shot from fr.png
- text: warframe,cliff,pose
  parameters:
    negative_prompt: DeepNegative_xl_v1
  output:
    url: images/xyz_grid-1088-3575876663-warframe,cliff,pose.png
- text: >-
    no visible face,sensuous,digital art,performance vehicle,foggy
    atmosphere,(ibex wearing headband),armored jacket,freedom,high
    cheekbones,glowing light lines
  parameters:
    negative_prompt: DeepNegative_xl_v1
  output:
    url: >-
      images/xyz_grid-1094-4137648909-no visible face,sensuous,digital
      art,performance vehicle,foggy atmosphere,(ibex wearing headband),armored
      jacket,freedom,high ch.png
- text: masterpiece,  best quality,
  parameters:
    negative_prompt: DeepNegative_xl_v1
  output:
    url: >-
      images/xyz_grid-1116-3748602630-masterpiece,  best quality,_The building
      looks like a giant twisted ribbon, curving and looping around itself. It
      is made of gla.png
base_model: stabilityai/stable-diffusion-xl-base-1.0
instance_prompt: null
license: unknown
---
# DeepNegativeXL

<Gallery />

## Model description 

### Put it in negative prompt box, everything to better!

This is the XL version of &#x60;DeepNegative&#x60;. If you are using the 1.5 model, please [click here](https:&#x2F;&#x2F;civitai.com&#x2F;models&#x2F;4629&#x2F;deep-negative-v1x)

# DeepNegative XL
Finally, it&#39;s released! try it and review~🤗

## What does it do?
**DeepNegative** is a negative embedding. it contain unsightly compositions and color patterns, such as inaccurate human anatomy, distasteful color combinations, disoriented spatial structures, and more. By put it in negative prompt, we can significantly reduce the occurrence of these elements.

## Suggestion
Because this embedding is learning how to create disgusting concepts, it cannot improve the picture quality accurately, so it is best used with (worst quality, low quality, logo, text, watermark, username) these negative prompts.

Of course, it is completely fine to use with other similar negative embeddings.

----
ps:
I apologize for not updating the Deep Negative XL model due to the excessive focus on text models... (god damn GPT model, it’s all commercial hype!)...

But now, though late, this is truly useful! 👾




## Download model

Weights for this model are available in Safetensors format.

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