Model
Trends
.ai
Model
Trends
.ai
the best open source ai models
Home
/
STABLE DIFFUSION XL 1.0
/
Boring SD XL Negative LORA: Enhance Images Stylistically AND Topically
Boring SD XL Negative LORA: Enhance Images Stylistically AND Topically
Share
NSFW
NSFW model. Its pictures are hidden while NSFW is off; turn NSFW on to see them.
Run Locally
boring_SDXL_negative_LORA_AutismMix_v1.safetensors
650 MB · SafeTensor
Downloads are served by Civitai. Some creators ask for a Civitai login first.
About This Model
Compare
STABLE DIFFUSION XL 1.0 · LoRAs
Created by
85014265776ef5720
on Civitai
Creator notes
Inspired by the popular Boring_e621 negative embedding , this is a negative LORA trained on thousands of images across years of data from different boorus with 0 favorites, negative scores, and/or bad tags like "low quality." Therefore putting it in the Negative Prompt tells the AI to avoid these things, which results in higher quality and more interesting images. Pros: -Generally increases quality which means more details, better depth with more shading and lighting effects, brighter colors and better contrast Could be Pro or Con depending on what you want: -Tends to generate more detailed backgrounds -Tends towards a more detailed or even more realistic look Cons: -Many of the training images were low resolution sketches or MSPaint style doodles, if you are trying to generate sketches or doodle style work putting this in the negatives may be detrimental -Many of the training images were black and white sketches or otherwise monochrome/grayscale, if you are trying to generate images without color putting this in the negatives may be detrimental -Accidentally putting this in the positive prompt instead of the negative prompt reduces the quality of images Test images was done using a weight of 1 with only this LORA in the negative prompt. You can adjust the weight of the LORA to change the impact, however in my testing the impact of different weights was minimal. The first version uploaded "boring_SDXL_negative_LORA_SeaArtXL_v1" was trained on the Sea Art XL model () and is intended to be used with that model. The second version was trained for AutismMix SDXL (). Please feel free to request if you want a version trained specifically for any other SD XL model.
3,533 downloads · 224 likes on Civitai
SHA256
58675C8E53EA296C7A5CA58D1923E0C8D469EFF3468A040FD65AE44E7553274A
ModelTrends.ai Model ID
#9587
Flag content
Example renders
Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
4
Seed
48563309
Size
1024x1024
Clip skip
2
Weight used
-0.5
Prompt
score_8_up, score_7_up, (by xnirox), solo, ((feral)) sylveon, side view, smug, rating_safe, by reallynxgirl
Negative prompt
(e621p_low), poorly drawn, bad anatomy, bad proportions, brush strokes, 3d, glitch, signature, watermark, bad face, distorted face, messed up eyes, deformed, missing arm, dull colors, extra limbs, male,
Settings
Sampler
Euler a
Steps
20
Guidance
5
Seed
845893366
Size
1024x1024
Clip skip
2
Weight used
-0.2
Prompt
score_9, score_8_up, score_7_up, ((feral)), raccoon, smug, 2d, smug, headshot portrait, solo, by kuroodod
Negative prompt
score_6, score_5, score_4, censored, child, kid, chibi, 3d, monochrome, elven ears, watermark, ((anthro))
Settings
Sampler
DPM++ 2M
Steps
31
Guidance
5
Seed
3450589644
Size
1536x1536
Weight used
-0.35
Prompt
score_9, score_8_up, score_7_up, (ultra realistic, 32k, masterpiece:1.2), (high quality:1.1), feral, dragon, (by zonkpunch, by chunie, by darkgem, by dimwitdog), huge wings, smug, neck bow, dapper, holding a cup of tea, looking at viewer
Negative prompt
civit_nsfw, easynegative, ng_deepnegative_v1_75t, bad quality, grainy, blurry, signature, patreon, logo, (worst quality, low qulaity:1.4), bad-hands-5,mutation,bad anatomy, backlit,comic,bad eyes,greyscale, bad_pictures, simple background, bad anatomy. Watermark, glans, bad_pictures, negative_hand, ng_deepnegative_v1_75t, shite fur, white body, wounds, Score_6, score_5, score_4, low poly, bad quality, ugly, ugly face, poorly drawn face, blurry, blurry face, (3d)
Settings
Sampler
DPM++ 2M Karras
Steps
34
Guidance
4
Seed
1411064383
Size
1024x1024
Clip skip
2
Weight used
1
Prompt
score_9, score_8_up, score_7_up, Succubus, egirlthot, EGirlMakeup, colorful makeup, neon fishnets, rainbow see through top, long tongue, needy, aroused, tight outfit, seductive expression, drool, sweat, purple skin, medium breasts, bare midriff, full body portrait, legs on display, succubus tail, ravenous, eye contact, staring at viewer hungrily
Negative prompt
monochrome, greyscale, portrait, 3d, censored, fewer digits, extra digits, score_6, score_5, score_4, zPDXL-neg, ((human skin)),
Settings
Sampler
Euler a
Steps
27
Guidance
5
Seed
3370426728
Size
1856x1280
Weight used
-0.2
Prompt
score_9, score_8_up, score_7_up, ((feral)), espeon, dapper, neck bow, smug, detailed fur, sign, mammal, feet, looking at viewer, toe claws, toes, open mouth, digital media (artwork), tongue, absurd res, (forest path, forest, city, nature, trees, grass, fog)
Negative prompt
civit_nsfw, score_6, score_5, score_4, censored, child, kid, chibi, 3d, monochrome, elven ears, watermark, ((anthro))
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
7
Seed
1548992174
Size
1024x1024
Clip skip
2
Weight used
1
Prompt
core_9, score_8_up, score_7_up, score_6_up, score_5_up, score_4_up, digital eye, body stained with brown oil, yellow line, black and green skin, monoeye, cyclops, half-closed eyes, Robot girl, Mecha, Android, mechanical limbs, robot joints, metal skin, black sclera, no mouth, armor, glowing eyes, no face, EasyNegativeV2, Robot Skin, Android Skin
Negative prompt
low quality face, low quality eyes, low quality, low quality eyes, too many fingers, multiple queues, too many arms, too many penises, two eyes.score_4, score_5, score_6, (low quality:1.3), (strong blurry), text, username, watermark, cloned face, unusual anatomy, watermark, amputee, (blurry eyes, stupid eyes, bad eyes), glitch, error
Settings
Sampler
DPM++ 2M Karras
Steps
34
Guidance
4
Seed
1511057253
Size
832x1216
Clip skip
2
Weight used
-1
Prompt
score_9, score_8_up, score_7_up, score_6_up, <lora:Humb3rt0XLP:1> humb3rt0, 1girl, solo, egyptian girl, hime cut, dark hair, nearly purple hair, black button down shirt, gold colored tie, short leather skirt, huge breasts, boob peek, thick thighs, tongue out, winking, green eyes, bright eyes, strappy sandals, cat girl, sphinx girl, hiding ears, gold thigh strap, long brown jacket, circular black rimmed glasses, toned arms, toned legs, tanned skin, dark skin, complex background, music club, performing on stage, singing,
Negative prompt
watermark, signature, artist name, 3d, muscular, cum, ugly, strange face , tanlines, black and white, white skin, easynegative, cats, white woman
How this score adds up
Every number on this site can be checked. The heat score of Boring SD XL Negative LORA: Enhance Images Stylistically AND Topically is 7,925°, and this is the receipt: the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. Hover over or tap any item for a plain-language explanation; the glossary at the end defines every term.
7,000°
7,925°
7,000°
Floor
Every model with real popularity data starts at 7,000°. Models without any data get a lower stand-in number so the lists are never empty, and a stand-in never ranks above a model with data.
+1,064°
Civitai downloads
3,533 downloads of this exact version on Civitai. Downloads are the heaviest ingredient and are counted on a log scale: ten times the downloads adds the same 300°, so a model with a million downloads is not a thousand times hotter than one with a thousand. The five download sources share that one term, split between them in proportion to their counts.
+353°
Likes
224 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
−492°
Age of the weights
−492° because the SDXL weights came out in 2023. Every model inherits the age of the weights it is built on: 150° a year, up to 750°, and it keeps growing until then. Without it the top of the list would be 2022 and 2023 checkpoints on the strength of downloads that had years to pile up.
= 7,925°
Heat score
Step by step
  1. 1
    Start at the floor.
    Every model with real popularity data begins at 7,000°.
    7,000°
    running total
  2. 2
    Add the downloads.
    3,533 download-equivalents in all, from Civitai downloads. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
    +1,064°
    8,064°
    running total
  3. 3
    Add the likes.
    224 likes and thumbs up, at half the weight of a download.
    +353°
    8,417°
    running total
  4. 4
    Take off the age of the weights.
    The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.
    −492°
    7,925°
    running total
  5. =
    The heat score.
    Where this model stands on every list of this site. Nothing else adjusts it.
    7,925°
The same slices over the last twelve months, or since the model's first day. Downloads, likes and runs follow the model's reconstructed curve, the red band is the age penalty as it stood on each date, and the white line is the score. The split between the download sources is today's; the speed, the bonus and the boost are shown as they are today.
Glossary: the terms used here
Heat score
One number for how much a model is used and wanted right now, from 0° to 9,999°. Every list on this site that says hottest is sorted by it and nothing else.
Floor
The 7,000° every model with real data starts from. Numbers below it are stand-ins for models without data.
Download-equivalents
Everything the score treats as a download, added up: downloads themselves, each torrent seeder as 1,000, each AI Horde image and each run on a generation site as one.
Log scale
Counting by tens, not by ones: going from 1,000 to 10,000 downloads adds the same degrees as going from 10,000 to 100,000. It keeps giants from crowding out everything else.
Likes
Thumbs up and likes from every source, worth half a download each on the log scale.
Download speed
How many downloads a day a model gets right now, from the difference between two readings of a source. A quarter of the weight of the download term.
Measured and estimated
Measured means two readings of a source exist and the difference is real. Estimated means only today's total is known and the past is spread over the model's life; the site says which one it is showing.
Seeder
Someone who keeps a copy of the weights online for others to download over a torrent, or a hosted mirror doing the same. Each one counts as 1,000 downloads.
AI Horde
A volunteer network that generates images for free on donated computers. The number of images it has made with a model is public, and each counts as one download.
Generation sites
Sites that host their own copies of a model and let people generate with it, such as PixAI, SeaArt and Yodayo. Their downloads count like Civitai's and each generation run as one download.
Graydient runs
How often a model has been run on Graydient, counted like downloads.
Full model (checkpoint)
The weights themselves, the file that generates on its own. It gets a bonus because add-ons depend on it.
LoRA and embedding
Small add-on files that steer someone else's weights toward a style, a character or a concept. They cannot run alone.
Family and weights
The base a model is built on, such as SD 1.5, SDXL, Flux or Wan. Every model inherits the release date of its family's weights.
Age of the weights
Degrees taken off for how long ago the family's weights came out: 150° a year, up to 750°. It keeps old downloads that had years to pile up from freezing the top of the list.
Family boost
A small, bounded nudge for LoRAs of a family this site is pushing forward right now, always listed in the breakdown.
Stand-in score
A stable number below the floor given to a model no source reports on yet, so lists stay complete. It never ranks above a model with data.
Trend
How a model's growth over a period compares with the typical model's growth over the same period. Faster than typical reads as a rise, slower as a fall.
Typical model
The middle of the catalog: half the models with a figure grew faster over the period, half slower.
Popularity trend
How this model's popularity has moved against the rest of the catalog: its growth in downloads, likes and usage over each period, measured against the typical model's growth over the same period, with its heat score at the time. Above the typical growth reads as a rise, below it as a fall. The past is reconstructed from today's totals, the model's first day and its measured download speed where two readings exist; a model that did not exist at the start of a period shows n/a.
This week
▼
0.3%
7,927° then, 7,925° now
This month
▼
1.3%
7,932° then, 7,925° now
Past year
▼
7.9%
7,973° then, 7,925° now
No second reading of the sources yet, so the curve spreads today's totals evenly over the model's life. It sharpens as the daily syncs add readings.
First seen 29 Apr 2024.
Embed this chart on your page or share this page. The chart is redrawn from the catalog each time it is shown, so it follows the model, and it links back to this page.
Share
AI Models for Image, Video & Text Generation
Boring SD XL Negative LORA: Enhance Images Stylistically AND Topically is a LoRA for the Stable Diffusion XL 1.0 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion XL 1.0 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
Browse by Model Family
Browse all models