Deep Negative XL

Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.

PirateDiffusion Telegram

Pro studio (SpyGlass) Web

Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.

Best for power users. Full control over models, settings and workflows in a browser studio.

Discord bot (Vector)

Best for communities. Add it to your own server and run any workflow from a channel.

Unified Editor Web

One screen for every model and workflow: prompts, references, edits and video, built into your Graydient account.

Civitai Web

Pay per use

Generate on Civitai's own site; every image is paid for with Buzz credits.

Local apps

Requires setup

Set up local programs if your computer has capable hardware.

ModelDuel Web

Pay per use

Generate the same prompt on up to 50 checkpoint/base models at a time.

Rent a GPU on the cloud

Graydient Cloud GPU

35,211 downloads · 1,709 likes on Civitai

Flat fee, unlimited use. This model installs with one click.

RunPod Cloud GPU

Charged by the minute

Rent a GPU by the minute and set the model up yourself.

Created by

lenML

on Civitai

by lenML - Deep Negative XL

Creator notes

Put it in negative prompt box, everything to better! 😎 This is the SDXL version of DeepNegative. another deep-negative: - 1.5 version: - pony version: Deep Negative XL Finally, it'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:1) 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! 👾

Trigger words

DeepNegative_xl_v1

SHA256

EABFB312E2DF431E55A3EDF35707B00CC0D920DC08C4E5AA26530D5E302225E0

Deep Negative XL Popularity Trend

Heat score, last 12 months

Heat score

8,358°

This week

▲

0.2%

8,360° then, 8,358° now

This month

▲

0.7%

8,364° then, 8,358° now

Past year

▲

16.0%

8,409° then, 8,358° now

7,000°

Floor

The scale runs from 0° to 9,999°. Everything below 7,000° is kept for models no source reports on yet, which carry a stand-in number there so lists stay complete. 7,000° is where measured data begins: a model with real data but almost no downloads sits at the floor, and the measurements fill the degrees above it. The floor says nothing about the model; only the degrees above it do, and they are what separates one model from another.

+1,303°

Civitai downloads

35,211 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 six download sources share that one term, split between them in proportion to their counts.

+67°

Generation sites

1,796 downloads and generation runs of this model's copies on SeaArt. Each run counts as one download, and their downloads count like Civitai's; all of it shares the download term.

+485°

Likes

1,709 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

−497°

Age

−497° 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.

Show detailed breakdown

Every number on this site can be checked. This model's heat score is 8,358°, and here it is built one ingredient at a time, with the running total after each: the floor, the degrees each source adds, the bonus for the kind of model and what the age of its weights takes away. The colors are the bands of the chart above. The glossary at the end defines every term.

1
Start at the floor.
Why 7,000° and not zero: the scale runs from 0° to 9,999°, and the part below 7,000° is reserved for models no source reports on yet, which carry a stand-in number there so the lists stay complete and never outrank a model with data. 7,000° is where measured data begins. A model with real data but almost no downloads sits here; everything that follows is measurement, and the room above the floor holds ten tenfold steps in downloads at 300° each. The floor is the same for every model, so it decides nothing; the degrees above it do.
7,000°
running total
2
Add the downloads.
37,007 download-equivalents in all, from Civitai downloads, Generation sites. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+1,303° Civitai downloads
+67° Generation sites
+1,370°
8,370°
running total
3
Add the likes.
1,709 likes and thumbs up, at half the weight of a download.
+485°
8,855°
running total
4
Take off the age.
The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.
−497°
8,358°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,358°

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. The scale runs from 0° to 9,999°; the part below the floor is reserved for stand-ins (models without data), so that a model with data always ranks above one without. The floor is the same for everyone and decides nothing; the degrees above it are the measurement.
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.
Adoption rate: 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.
OpenRouter tokens: A text model served through an API, such as Claude or GPT, has no weights to download, so its usage is measured in tokens: the pieces of text it read and wrote through OpenRouter, a gateway many apps use, over the last 30 days. Every 10,000,000 tokens count as one download. Source: OpenRouter (openrouter.ai/rankings), CC BY 4.0.
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: 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.
New! (grace period): A model less than 7 days old shows New! instead of a score and holds no place in the rankings. Its score is computed from day one, but a model one day old grows faster than anything, so without the wait the week's #1 would always be whatever came out yesterday rather than what held up for a week.
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.

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.

Example renders

NSFW

Prompts and settings shared by the people who made these renders on Civitai. Pick a render to see how it was made.

NSFW render, blurred. Turn NSFW on to see it.

NSFW render, blurred. Turn NSFW on to see it.

NSFW render, blurred. Turn NSFW on to see it.

NSFW render, blurred. Turn NSFW on to see it.

Get this prompt

Render by EcstaticKalliope on Civitai

Settings

Sampler

DPM++ 3M SDE

Steps

Guidance

4.5

Seed

2506650012

Size

768x1152

Clip skip

Prompt

apture a photo-realistic image of a snake with dragon horns, no legs, adorned with black scales featuring intricate red and gold patterning. The snake should have colorful, beautiful eyes and be depicted in a dynamic full-body pose. Utilize cinematic lighting with Rembrandt lighting techniques to create depth and drama in the image. Incorporate volumetric lighting to enhance the atmosphere around the snake. The photograph should be taken with an aperture of F/2.8 to create a shallow depth of field and focus attention on the subject. Ensure maximum detail and ultra-realism in the rendering. The snake should be centered in the frame, commanding attention and exuding beauty and majesty. The overall composition should be visually captivating and showcase the intricate details of the snake's scales and horns. (Dramatic Lighting, Photography, 3D Illustration, Vibrant Colors, Exquisite Detail, Award Winning, Stunning) <lora:MJ52:0.5> epiCPhoto

Negative prompt

(low quality, worst quality) EasyNegative bad-hands-5 ng_deepnegative_v1_75t (deformed) score_6, score_5, score_4, extra limbs, extra digits, DeepNegative_xl_v1 negativeXL_D, ((watermark, logo, signature)) (nipples)

Render by EcstaticKalliope on

Civitai

Prompt on BunchaPrompts

Render by AquaShades on Civitai

Settings

Sampler

DPM++ SDE

Steps

Guidance

3.5

Seed

3361203181

Size

768x1152

Clip skip

Prompt

Painting of a bug-eyed nervous chihuahua wearing a pink tutu inspired by Girl With The Pearl Earring. Girl with a Pearl Earring (Dutch: Meisje met de parel)[1][2] is an oil painting by Dutch Golden Age painter Johannes Vermeer, dated c. 1665. Going by various names over the centuries, it became known by its present title towards the end of the 20th century after the earring worn by the girl portrayed there.[3] The work has been in the collection of the Mauritshuis in The Hague since 1902 and has been the subject of various literary and cinematic treatments. <lora:detailed_notrigger:0.6> <lora:SDXLFaeTastic2400:1> <lora:MJ52:0.8> (Photography, Ultrarealistic, 3D Illustration, Exquisite Detail)

Negative prompt

(low quality, worst quality) EasyNegative bad-hands-5 ng_deepnegative_v1_75t (deformed) score_6, score_5, score_4, cape, jacket, extra limbs (nipples, nude, ass) DeepNegative_xl_v1

Render by EcstaticKalliope on Civitai

Settings

Sampler

euler_smea_dy_cfg_pp_beta_1_1

Steps

Guidance

1.5

Seed

418787544052609

Size

1664x2432

Clip skip

Prompt

1girl, full body, masterpiece, best quality, amazing quality, ultra-HD, cinematic lighting, photorealistic, impressionism, high detail, depth of field, bokeh, very aesthetic, 8k, [by dino \(dinoartforame\)|by quasarcake|by raikoart], BREAK horse girl, horse ears, red eyes, long hair, multicolored hair, black hair, white hair, katana, kimono, absurdly detailed composition, toned female, medium breasts, samurai girl, moonlight, shoulder armor, armor, castle, dungeon, night, stars, BREAK [by cromwellb|by rejean dubois|by mukakin|by putcher|by raskasar|by the golden smurf] BREAK usnr, [by nixeu|by zumi \(zumidraws\)|by sakimichan|by olchas|by luminyu|by murata taichi]IllusP0s,

Negative prompt

(worst quality, low quality:1.4), watermark, patreon username, patreon logo, old, early, lowres, signature, username, logo, bad hands, mutated hands, jpeg artifacts, watermark, missing fingers, extra digits, distorted anatomyStable_Yogis_Animetoon_Negatives-neg, DeepNegative_xl_v1,

What is ComfyUI? A beginner's guide to nodes, workflows and the first graph

Settings

Sampler

DPM++ 2M SDE

Steps

Guidance

3.5

Seed

682501366

Size

768x1024

Clip skip

Prompt

a fine art sculpture photo of a distorted malfunction silver metallic skinny robot arm tangled with a wooden frame with detail casting on it, some electronic cables are leaking from the vase, textured and rough surface, high details, on a grunge grid wooden table in dim museum, in the style of biomorphic sculpture and Solarpunk art, beige and white, fine attention to anatomy, close up, mushroomcore, animal bone, lovely brushstrokes, Vintage, Surrealism, half light half shadow, low contrast, fujifilm <lora:detailed_notrigger:0.6> <lora:SDXLFaeTastic2400:0.6> (Exquisite Detail, Award Winning, Stunning)

Negative prompt

(low quality, worst quality), (deformed), score_6, score_5, score_4, extra limbs, DeepNegative_xl_v1, extra digits, negativeXL_D, bad hands, (nude, nipples, ass), logo, watermark, ((multiple tails))

Run Locally

How to install

Dec 17, 2025

Open Civitai Download

DeepNegative_xl_v1.safetensors

0 MB · SafeTensor · fp16

Downloads are served by Civitai. Some creators ask for a Civitai login first.

marie claude bourbonnaise

LORA

LORA

rainbowplasm

Anime Screenshot Merge NoobAI

LORA