Moxie Diffusion 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

2,094 downloads · 148 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

moxie1776

on Civitai

Moxie Version 1.51 Lightning SDXL by Moxie1776. Formerly Turbo Diffusion XL is a merge of Juggernaut, Dreamshaper, Copax, Vibrant Horizon, and Sleipnir Lightning models. Recommended settings: /sampler:dpm2m /karras /steps:8 /guidance:2 /clipskip:2

Creator notes

Formerly Turbo Diffusion XL v1.91 It seems the problem was ZavyChromaXL.. - Primary: - Secondary: v1.9 I am fairly adamant to use only trained checkpoints when creating these checkpoints. I was excited to see with Zaxious now has a trained checkpoint. I'm pretty curious to play more with this. So far, I'm liking this version quite a bit. - Primary: - Secondary: - v1.8 I have typically liked ProtoVision and DynaVision more, and used NightVision sparingly. However, lately I like NightVision the best. It seemed like time to incorporate it since there were new releases of NightVision and Zavy (Zavy being one of my long time favorites). - Primary: - Secondary: - Tertiary: v1.7 Fully SDXL version... - Primary: - Secondary: - Tertiary: Lightning Versions v1.6 Crystal clear has been in my top 3 almost continuously since I found it. I was excited when I saw they posted a Lightning version. - Primary: - Secondary: v1.51 This is a low percentage merge. I don't find a large difference between 1.50 and v1.51. However, the comparison images seem to be a little sharper and more realistic. I decided to do this merge after playing with the donor checkpoints. - Primary: - Secondary: - Tertiary: v1.5 As I have been playing more with v1.4, I am finding that I am not as happy with the realism as I initially thought. I resetting it by merging checkpoints of some of my favorite trained checkpoints. - Primary: - Secondary: DreamShaperXL Lightning DPM++ SDE - Tertiary: As I have been playing more with v1.4, I am finding that I am not as happy with the realism as I initially thought. I resetting it by merging checkpoints of some of my favorite trained checkpoints. - Primary: - Secondary: - Tertiary: v1.4 - Primary: (now Moxie Diffusion XL) - Secondary: - Tertiary: v1.32 This version is a complete ground up re-make using SDXL Lightning checkpoints. - v1.30 unpublished - Primary: (unpublished) - Secondary: - Tertiary: - v1.31 - Primary: Turbo Lightning v1.30 (unpublished) - Secondary: - Tertiary: - v1.32 - Primary: Turbo Lightning v1.31 (unpublished) - Secondary: - Tertiary: This has a baked in VAE. - Sampling Method: DPM++ SDE Karras - Sampling steps: 7 - CFG Scale: 1 - Clip Skip: 1 or 2 Turbo Versions v1.2 The anime in this version seems to be more of a realism anime. - Primary: (this checkpoint) - Secondary: v2 Turbo DPMpp SDE - Tertiary: v1.0 v1.12 A re-merge of 1.0 using Vibrant 2.0 instead of 1.0. Everything else remains the same. - Primary: (this checkpoint) - Secondary: v2.0 - Tertiary: v1.1 - Primary: (this checkpoint) - Secondary: v1.0 - Tertiary: v1.0 This checkpoint is a Stable-Diffusion merge between the follow 3 SDXL Turbo models. - Primary: - Secondary: - Tertiary: This has a baked in VAE. - Sampling Method: DPM++ SDE Karras - Sampling steps: 8 - CFG Scale: 2 > 3.5 - Clip Skip: 1 or 2

SHA256

5C19630A582BA316E087DE9E435DBF2628E7018A41B253816345E3E16E90A865

Ranking badge

Updated Oct 22, 2026

Made this model? Show this badge on your page.

Paste it into your Hugging Face card or Civitai description.

Change colors / personalize / get code

Not this creator?

Get your own badge

Moxie Diffusion XL Popularity Trend

Heat score, last 12 months

Heat score

8,055°

This week

▼

0.5%

8,058° then, 8,055° now

This month

▼

2.3%

8,068° then, 8,055° now

Past year

▼

27.3%

8,197° then, 8,055° 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.

+676°

Civitai downloads

2,094 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.

+385°

Generation sites

1,202 downloads and generation runs of this model's copies on PixAI. Each run counts as one download, and their downloads count like Civitai's; all of it shares the download term.

+333°

Likes

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

+8°

Adoption rate

About 0 downloads a day, measured between two readings of the sources, never guessed from a lifetime average. Speed weighs a quarter of the download term, so a fresh surge shows without letting a one-day spike outrank years of use.

+150°

Full model

+150° because this is a full model: a checkpoint, the weights themselves. A LoRA or an embedding is an add-on to someone else's weights and does not outrank a checkpoint of equal popularity.

−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 8,055°, 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.
3,296 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.
+676° Civitai downloads
+385° Generation sites
+1,061°
8,061°
running total
3
Add the likes.
164 likes and thumbs up, at half the weight of a download.
+333°
8,394°
running total
4
Add the adoption rate.
About 0 downloads a day right now, measured between two readings, at a quarter of the weight.
+8°
8,402°
running total
5
Bonus for a full model.
A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.
+150°
8,552°
running total
6
Take off the age.
The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.
−497°
8,055°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,055°

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

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

Get this prompt

Render by moxie1776 on

Settings

Sampler

DPM SDE

Steps

Guidance

Seed

3624365226

Size

832x1216

Prompt

futuristic style virtual reality, augmented reality, gritty urban cyberpunk person, moody atmospheric perspective, cybernetic implants, mechanical arms, mechanical left eye, drawing from style of Chris Cold or HR Giger or Guweiz, . sleek, modern, ultramodern, high tech, detailed,

Negative prompt

ugly, deformed, noisy, blurry, low contrast, realism, photorealistic, vintage, antique, nsfw, nude, topless, (cleavage:1.2), (cleavage cutout:1.2), nipples, bulge, vagina, indoors, simple background, narrow shoulders, , plastic, long neck, asymmetrical eyes, signature, watermark, jpeg artifacts, cropped,,,

Render by moxie1776 on

Settings

Sampler

Default

Steps

Guidance

Seed

3944254178

Size

832x1216

Prompt

macabre style Midnight, churning black seas, a weathered galleon with tattered sails bursts from shadowy depths, its hull silhouetted against a blood-red moon, sails billowing full of wind, a colossal kraken rises from the depths, tentacles thrashing, snapping jaws dripping with bioluminescent venom, style of Frank Frazetta, waves crashing against the ship, ominous foreboding atmosphere. . dark, gothic, grim, haunting, highly detailed

Negative prompt

bright, cheerful, light-hearted, cartoonish, cute, asian, plastic, long neck, asymmetrical eyes, signature, watermark, jpeg artifacts, cropped, username, artist name

Render by Roundfire4746 on

Settings

Sampler

Euler a

Steps

Guidance

Seed

Size

1152x1920

Prompt

score_9, score_8_up, score_7_up,score_6_up, score_5_up, score_4_up ,Create an image capturing a Halloween theme featuring a floating Jack-o'-lantern in the middle of a cornfield. The scene should evoke a sense of mystery and enchantment, highlighting the classic elements of Halloween. The Jack-o'-lantern should be illuminated from within, casting an eerie glow on the surrounding corn stalks. The night sky should be dark and scattered with stars, with a full moon adding to the ambiance. Consider incorporating gentle fog or mist to enhance the mystical atmosphere. The color palette should primarily consist of dark blues, deep oranges, and subtle greens, emphasizing the spooky yet magical theme. Pay attention to details in the texture of the pumpkin and the leaves of the corn to bring the scene to life. style of Simon Bisley, embedding:zPDXL3, embedding:pny-safe, embedding:fixl-art, embedding:zPDXL, <lora:PonyBackgroundDetailerV2:1> <lora:bettershading:0.75> <lora:xl_more_art-full_v1:1> <lora:SDXLFaeTastic2400:0.8> High dynamic range, vivid, rich details, clear shadows a embedding:easynegative, , High dynamic range, vivid, rich details, clear shadows and highlights, realistic, intense, enhanced contrast, highly detailed

Negative prompt

watermark, text, signature, and "greyscale" score_6_up, score_5_up, score_4_up, embedding:pony_negativeV2, embedding:BeyondSDXLv3, embedding:pny-NEG-text, embedding:NEG-fixl-2, embedding:zPDXL-neg, , (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, grayscale, bw, bad photo, bad photography, bad art:1.4), (watermark, signature, text font, username, error, logo, words, letters, digits, autograph, trademark, name:1.2), (blur, blurry, grainy), morbid, ugly, asymmetrical, mutated malformed, mutilated, poorly lit, bad shadow, draft, cropped, out of frame, cut off, censored, jpeg artifacts, out of focus, glitch, duplicate, (airbrushed, cartoon, anime, semi-realistic, cgi, render, blender, digital art, manga, amateur:1.3), (3D ,3D Game, 3D Game Scene, 3D Character:1.1), (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3) , simplified, abstract, unrealistic, impressionistic, low resolution , flat, low contrast, oversaturated, underexposed, overexposed, blurred, noisy, low quality, low resolution

Render by TomTomorrow on

Settings

Sampler

heunpp2_beta

Steps

Guidance

3.6

Seed

475314524309126

Size

832x1216

Clip skip

Prompt

Background, an enchanted forest of fairies and satyrs (embedding:DarkWorldDreams-2-SDXL:0.5) (materials:dark crystal, polished metalic gold highlights, plasma:1), (dark saturated colors:1.5) (sacred geometry:1.3), fractal patterns anm-frac style, (three-dimensional:1.5), (complex dodecahedron structure:1.3), (Fibonacci-based layering:1.3), (cube or monolith hybrid base form:1.4), (chaotic randomness in geometry:1.2), (prismatic glow:1.3), (internal illumination pulses:0.7), (visible energy fields or currents:1.3), (extremely fine detail:1.5), (broad depth of field emphasized:1.0), (lightly patterned backdrop), (sci-fi, dimensional ambiguity)

Negative prompt

(((border on edge, white strip))), (dark, poorly lit, shadows:1.2) (((Grainy))), ((childish, silly, cartoon))), globe, ball, (Up close view), ((woman, alien)), ((name, writing, letters, trade mark, signature, logo)), simplistic, Photo ugly Cartoon (worst quality, low quality, normal quality) man, woman, child, symmetric

Render by moxie1776 on

Render by Roundfire4746 on Civitai

Settings

Sampler

dpmpp_2m_sde_gpu_sgm_uniform

Steps

Guidance

Seed

Size

832x1216

Prompt

biomechanical cyberpunk portrait capturing the essence of a young cyborg woman with fiery red hair. Her face fills the frame, bathed in neon hues, exuding determination and mystery amidst a futuristic backdrop, . cybernetics, human-machine fusion, dystopian, organic meets artificial, dark, intricate, highly detailed

Negative prompt

natural, colorful, deformed, sketch, low contrast, watercolor, nsfw, (cleavage:1.2), (cleavage cutout:1.2), nipple, vagina, bulge, plastic, long neck, asymmetrical eyes, signature, watermark, jpeg artifacts, cropped, username, artist name

Render by Roundfire4746 on Civitai

Settings

Sampler

DPM++ 2M SDE Karras

Steps

Guidance

Seed

Size

1152x1920

Prompt

Negative prompt

Settings

Sampler

DPM++ 2M SDE Karras

Steps

Guidance

Seed

Size

1152x1920

Prompt

Negative prompt

Render by moxie1776 on

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

Settings

Sampler

Default

Steps

Guidance

Seed

3090117317

Size

832x1216

Prompt

renaissance style impressionist painting of an enchanting nightscape, daisies bloom under under a tapestry of stars, daisy petals adorned with celestial patterns, fireflies dance among them like shooting stars, warm moonlight casts an ethereal glow, casting a magical glow upon the nocturnal garden, inspired by Van Gogh's 'The Starry Night' . realistic, perspective, light and shadow, religious or mythological themes, highly detailed

Negative prompt

ugly, deformed, noisy, blurry, low contrast, modernist, minimalist, abstract, plastic, long neck, asymmetrical eyes, signature, watermark, jpeg artifacts, cropped,

Run Locally

How to install

Dec 17, 2025

Open Civitai Download

moxieDiffusionXL_v191.safetensors

6.81 GB · SafeTensor · fp32 · full

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

More by this creator

Moxie Diffusion XL

Moxie Cybernetic & Punk Lora's

BASE

FLUX

Snoot Challenge | Concept LoRA XL

All models by moxie1776

Similar Models

ヴァニラ / もんむす・くえすと！ / もんむす・くえすと！RPG Vanilla: Monster Girl Quest! / Monster Girl Quest RPG

Anya Taylor Joy SDXL

Daiwa Scarlet (Umamusume) in game style 3D ILL v2