Lucky Strike Mix

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

15,974 downloads · 1,463 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

kinshin007

on Civitai

Lucky Strike v1.05 "Lovely Lady" by kinshin007 is the latest installment of the Lucky Strike checkpoint trained base models, used for 3D semi-realistic images though realism is also possible when LoRAs are in play. It's designed to make unique female characters though quite versatile for other uses

Creator notes

2023/7/28 展示图片主要是前几天和SDXL对照时生成的（没有使用lora），本来我是准备放弃这个模型的，意外的感觉还挺不错，并且相当有特点 The display pictures are mainly generated when comparing with SDXL a few days ago (without any LORA). I was planning to give up this model, but unexpectedly, it feels pretty good and quite distinctive. 兑现承诺，我会在这个帖子里把我主要的私模都整理发上来， To fulfill my promise, I will post all my main private models in this post, Welcome to follow my pixiv， Or support and get my generated work on patreon， 2023/3/30 hello everyone, I updated a few lora models that you all want, 与一般的真实系模型相比，Lucky Strike Mix提供了非常纤细的少女体型，并且通过Clip剪切，身体比例也是接近1:9（9头身），而非1：8 Compared with the general real model, Lucky Strike Mix provides a very slender girlish figure, and through Clip cutting, the body ratio is close to 1:9 (9 head body) instead of 1:8 0.2版本改善了手部的表现具体方法是通过脚本将所有ATTN1块信息更换为AOM2-NSFW的，然后将处理后的模型与v0.1流程中的模型混合，但是这个过程中出现了画面劣化的问题，所以我只混入了约50%的手部修正。 “Lucky Strike”的特色传统依然被保留（笑）。 Version 0.2 improves hand performance The specific method is to replace all ATTN1 block information with AOM2-NSFW through the script, The processed model is then blended with the model from the v0.1 pipeline, But there was a problem of image degradation in the process, so I only mixed in about 50% of the hand correction. The characteristic tradition of "Lucky Strike" is still preserved (laughs). .............................................................................................. 这个模型的初衷是画出纤细修长的大腿。 The original intention of this model is to draw slender and slender thighs，这个出发点是基本能满足，但是副作用是完全不会画手了。 This starting point is basically satisfactory, but the side effect is that I can't draw hands at all. Lucky Strike Mix这个名字也是因此而来，如果次数足够多，总会有完美的图片出现。 The name Lucky Strike Mix is also derived from this, if there are enough times, there will always be a perfect picture。 The following is the composition of the model base model： 0.7(0.5(Gf_style2) + 0.5(mixedmixedmixedV2)) + 0.3(basil_mix) replace OUT02,OUT04 with nightSkyYOZORAStyle_yozoraV1 --to get legs replace IN00,IN01 with AbyssOrangeMix2_nsfw --to get fingers then reset all clips to get basic weight set 虽然直接生成的图片是偏手绘的，但我保留了大部分真实光影，因此配合真实系的Lora使用，可以绘制更加真实的图片 Although the directly generated pictures are hand-painted, I kept most of the real light and shadow, so it can be used with the real Lora to draw more realistic pictures 需要注意的是，只有站立状态下的腿型是完美的（对我而言），其他姿势依然非常容易出错 It should be noted that only standing legs are perfect (for me), other postures are still very error-prone Welcome to follow my pixiv， Or support and get my generated work on patreon，

SHA256

80A6FFEE8D4611F0681874AA6D02CF3B943DDD340219D9489790F9923196DFE1

Lucky Strike Mix Popularity Trend

Heat score, last 12 months

Heat score

8,322°

This week

▼

0.5%

8,325° then, 8,322° now

This month

▼

2.3%

8,333° then, 8,322° now

Past year

▼

27.2%

8,464° then, 8,322° 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.

+1,276°

Civitai downloads

15,974 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.

+475°

Likes

1,463 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

+30°

Adoption rate

About 1 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.

−609°

Age

−609° because the SD15 weights came out in 2022. 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 8,322°, 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.
15,974 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.
+1,276°
8,276°
running total
3
Add the likes.
1,463 likes and thumbs up, at half the weight of a download.
+475°
8,751°
running total
4
Add the adoption rate.
About 1 downloads a day right now, measured between two readings, at a quarter of the weight.
+30°
8,781°
running total
5
Bonus for a full model.
A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.
+150°
8,931°
running total
6
Take off the age.
The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
−609°
8,322°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,322°

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

Settings

Sampler

DPM++ 2S a

Steps

Guidance

Seed

2789515522

Size

512x768

Clip skip

Prompt

1 supercute cat wear a origami gundam armor,fur

Negative prompt

EasyNegative, negative_hand-neg, (worst quality, bad quality:1.5), (low quality:1.5), lowres, monochrome, (greyscale:1.5), (yellow, orange, red:1.3),more then one navel,pussy,1girl,(humans:1.2),(girls:1.2),

Render by kyawkaung on Civitai

Settings

Sampler

DPM++ 2M alt Karras

Steps

Guidance

Seed

2361333932

Size

640x960

Clip skip

Prompt

(masterpiece:1.1), (best quality:1.1),25yo,NSFW, tachi-e, full body, white background, <lora:standingFullBodyWithBackgroundStyle_v10Offsetfo:1.2>, [(white background:1.5)::5], isometric,<lora:gachaSplashLORA_gachaSplashFantasy20:0.65> masterpiece,(((flat chest))),girl,delicate light,detailed eyes,highly detailed light,delicate limbs,nature,glow,frilled long skirt,gleaming purple eyes,floating swords,synesthesia,angel,floating beige hair,long floating hair,particle lighting,(detailed white victorian dress gloves shoulder armor angel wings),angle,intense shadows,motion blur ,style of Alfons Mucha, light painting, long exposure, dynamic streaks, luminous trails, vibrant colors, fluid movement, captivating patterns, creative experimentation narrow waist, bangs, <lora:no121Girl_no121Girl:0.25:char3>,(PureErosFace:0.7),(realistic:1), <lora:balenciaga:0.5:char3> ,(caustics:1.1), <lora:zhouzhou_zsyV10:0.35:char31><lora:koreanGalLoconLora_1:0>

Negative prompt

EasyNegative, negative_hand-neg, (worst quality, bad quality:1.5), (low quality:1.5), lowres, monochrome, (greyscale:1.5), (yellow, orange, red:1.3),more then one navel,

Settings

Sampler

DPM++ 2M Karras

Steps

Guidance

Seed

1749024261

Size

512x768

Clip skip

Prompt

BREAK (best quality, masterpiece, detailed:1.2), (RAW photo, photo realistic:1.3), absurdres, 8K UHD, high definition, ultra detailed, high quality texture, intricate details, detailed texture, finely detailed, high detail, extremely detailed cg, high quality shadow, (a beautiful busty 21 years old sexy woman:1.2), BREAK (pretty k-pop girl, korean mixed), (hair female), (brown hair:1.2), makeup, detailed beautiful delicate face, detailed beautiful delicate eyes, (big breasts, sagging breasts, cleavage:1.3), (big ass, wide hips, thin waist), (beautiful legs, thick thighs, thigh gap:1.1), (pleated skirt, white shirt:1.3), open shirt, (diamond necklace, bracelets, earrings, red beret:1.2), urban city street, (lens flare, sunbeams), cowboy shot, <lora:Saya-long breasts3:0.5>, <lora:GoodHands-vanilla:1.5>

Negative prompt

EasyNegative, verybadimagenegative_v1.3, (bag)

Settings

Sampler

DPM++ 2S a

Steps

Guidance

Seed

3559411940

Size

512x768

Prompt

screenshot of person's profile in Tinder app, buttons of user interface, her name and age in large headline text, self-introduction paragraph written, with photo of attractive woman. Dating matchmaking smartphone application

Negative prompt

Settings

Sampler

DPM++ 2S a

Steps

Guidance

Seed

366869016

Size

512x768

Prompt

a supercute kitty wear Ultraman armor and Ultraman mask,

Negative prompt

Settings

Sampler

DPM++ 2S a

Steps

Guidance

Seed

3559411941

Size

512x768

Prompt

Negative prompt

Render by shirasachi on Civitai

Settings

Sampler

DPM++ 2S a

Steps

Guidance

Seed

1323330742

Size

512x768

Prompt

panda wearing Dracula costume on Halloween night in a spooky haunted house, winning photography, expert cinematography, dramatic lighting, dramatic scenery

Negative prompt