GhostMix
8839°
<ghostmix2>
Apps that support ModelTrends tags let you run/install models by copying this code in your prompt with no setup. Look for our icon in apps that support it, like Prism (below).
Run this model
Offers / Ads
Easy Creator (Prism) Web
Unlimited · flat fee
Best for beginners. Describe what you want in a chat and the picture comes back, no learning curve.
PirateDiffusion Telegram
Unlimited · flat fee
Images and video from a chat, with short commands. The most convenient tool for Telegram users, with a web companion.
Pro studio (SpyGlass) Web
Unlimited · flat fee
Best for power users. Full control over models, settings and workflows in a browser studio.
Discord bot (Vector)
Unlimited · flat fee
Best for communities. Add it to your own server and run any workflow from a channel.
Unified Editor Web
Unlimited · flat fee
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.
GhostMix by _GhostInShell_. GhostMix Version 2 is a full checkpoint base model focused on intricate artworks, inspired in part by the biomechanical style of Ghost in the Shell anime. It can also produce interesting effects with fractal and watercolor tags. Like many anime base models, it uses modified Danbooru tag method. The main deviation is a signature character that can be invoked with "1mechanical girl". This character appears more often when the aspect ratio is 512x768 or similar, and a guidance of 7 or less is recommended overall.
Creator notes
Any questions or corporations? Find me at or by Wechat: ghostinshell10. Thanks
You can run GhostMix on the cloud at Mage &
My model is now supported to create a short-form animation with the new "Animate" feature on Mage!
GhostMix V2 at:
GhostXL at:
GhostMix model at:
IMPORTANT MATTERS(重要事项)
-
I think compacity is the most important thing of a checkpoint, that's why I don't merge ANY LORA in GhostMix. Checkpoint solves the CAN DO problem and Lora solves the DO IT RIGHT problem. （我认为checkpoint最终要的是兼容性，所以我没有融任何lora进checkpoint，checkpoint应该解决的是做的到的问题，而lora解决的是做的对的问题）
-
Highres-Fix is A Must! Highres-Fix: 2x, denoising:0.4-0.5 or 1.5x, denoising:0.5-0.65. (一定要做高清修复! 高清修复: 2倍, 重绘幅度:0.4-0.5 或 1.5倍, 重绘幅度:0.5-0.65)
-
Make Sure you are in the right CLIP if you want to replicate my job, some themes are CLIP=1,while others are CLIP=2.Suggest download the image and put it into PNG info to check the setting (如果想要复现,确保CLIP值要对! CLIP1和CLIP2要对!建议把图下下来然后放到PNG信息里面去查设置)
-
Most Prompts in Previous Version of GhostMix can produce similiar result in New Version of GhostMix (之前用的大多数Prompts在新版本也可以生成相似的结果)
-
Textual Inversion&VAE: and ,don't use Bad-Hand V4 & V5！（用 和,别用BadHandV4,V5)
-
Sampler Suggest : DPM++ series , Steps: 20-30, CFG:5-7(7 is best)（采样方法建议 DPM++系列 , 步数20-30, CFG:5-7(7最好) ）
-
Suggest resolution: 512,768! mechanical girl theme is very sensitive to the resolution, not suggest make the aspect ratio too low.(建议分辨率:512,768! 机械少女主题对分辨率设置非常敏感，不建议设太低的宽高比)
If you want to support me, please buy me a coffee :
国内支付宝、微信用户可以通过爱发电给我买杯咖啡：
I create the world's first checkpoint review framework GhostReview, by using LAION Aesthetics, Clipscore, HPS, StyleLoss to measure ckpts quantitatively in Image Quality,Style Compatibility and LoRA Compatibility. If you want to see the detail, please check the article link below.
2023.5.21 GhostMix-V2.0 (fp16 pruned ver replaced)
UPDATE DETAIL(中文更新说明在下面)
Hello everyone, this is Ghost_Shell, the creator. The GhostMix-V2.0 significantly improves the realism of faces and also greatly increases the good image rate. In my tests at 512,768 resolution, the good image rate of the Prompts I used before was above 50%. It is more user-friendly. During making the GhostMix-V2.0, I adjusted 47 versions of the model and finally chose one of them.
大家好，这里是作者Ghost_Shell。这次GhostMix-V2.0大幅提升了脸的真实性，也大幅提升了良图率，在我测的512,768分辨率之下，之前用的Prompts良图率都在50%以上，对用户更加友好。这次在测试中一共调了47个版本的模型，最终选了一个。
Other Words I want to say(题外话):
To be honest, this may be the last version of GhostMix.On one hand, it is really inefficient to use 3060ti to make models. In the past two weeks, I have almost no free time except for making models and testing them. On the other hand, I temporarily feel that this model is almost at its limit and the space for improvement is really not high. I hope you like it. If you like the model, I hope you can post your images to Civitai. Many of the prompts I tested for GhostMix-V2.0 are from your posts, which is really important for me to test the model. If you can give it a 5-star rating, that would be great. If you are willing to support my work, please click: . My goal is to buy a 4070 and work more efficiently on making models. Using a 3060ti to make models is really inefficient and it basically cannot be used to test high resolution images.
说实话，这可能是GhostMix的最后一个模型，一方面3060ti去做模型真的效率太低了…最近两个星期基本没有空闲时间，除了做模型，就是测模型。另外一方面，我暂时觉得这个模型近乎极限，能提升的空间确实不高了，希望大家喜欢。如果大家喜欢模型，希望大家能post自己的作品到Civitai，这次测试的很多Prompts就是从你们post里面来的，这对我测试模型真的很关键，如果能5星评价就更好。如果愿意支持我的工作，请点击： 我的目标就希望能换一块4070，更高效的去做模型，3060ti真的测模型效率太低了，而且基本没法测更高分辨率的图片。
2023.5.1 GhostMix-V1.2 (fp16 version uploaded)
UPDATE DETAIL(中文更新说明在下面)
THIS IS NOT A 3D MODEL! THIS IS NOT A 3D MODEL! THIS IS NOT A 3D MODEL!
If you like my model，please give me 5 Stars ,it will encourage me a lot. Thanks!
Color Problem ：Check VAE is kl-f8-anime2 ？颜色问题：查VAE是否为kl-f8-anime2？
GhostMix V1.2 is an absolutely astonishing model, and I think it is the strongest 2.5D model in Civitai right now. I think a update of the model should improve the model’s compatibility, good image rate and image details given the main structure of 90% generated images doesn’t change. So I use layer combination to combine models layer by layer. And I got this model after 9 different versions of “the final version of GhostMix V1.2”,LOL.This version of GhostMix V1.2 is a balance in terms of compatibility, good image rate and image details, although sometimes using the same Promts of GhostMix V1.1, may comes up a different result.But this doesn’t happen too much.
PS: The first image of GhostMix V1.2 is a nod to Mamoru Oshii’s version of Ghost in Shell in 1995, and my name Ghost_Shell is also a nod to this movie.
中文更新说明
GhostMix V1.2是绝对让你惊艳的模型，也是自己认为现在最强的2.5D模型。我认为模型的更新应该是基于现有的画面整体不大变的前提下，提高模型的成图率，兼容性和画面细节。所以我采用了分层融合，一共做了9个版本的“GhostMix V1.2最终版本”，最终得到了现在这个版本的GhostMix V1.2。这个版本的GhostMix V1.2在兼容性，成图率和画面细节表现比较平衡，虽然有时候会出现同样的Promts，出图改变的情况，但实测不多。
PS：GhostMixV1.2的头图是致敬1995押井守版Ghost in Shell 攻壳机动队的生成的，Ghost in Shell也是作者名字的由来。
2023.3.11 GhostMix-V1.0
Introduction(中文简介在下面)
First of all , I want to thank all the people who use this Checkpoint. And this is my first Checkpoint.All the sample image can be reproduced. This Checkpoint works well on both SFW and NSFW.THE NSFW PART IS VERY GOOD!!!
I uploaded this Checkpoint yesterday and from yesterday to today , I am still trying all the possibility of this Checkpoint. So if you try the model and find some good promts , I hope you can upload it and share with me, it will help me for the next version of GhostMix, Thank you agian!
Recommend Some Promts:
-
Fractal Art（highly recommend，awsome）
(masterpiece, top quality, best quality, official art, beautiful and aesthetic:1.2), (1girl:1.3), (fractal art:1.3),
-
Color Art
(flat
VAE&Textual Inversion:
VAE: kl-f8-anime2 or vae-ft-mse-840000-ema-pruned(anime suggest: kl-f8-anime2)
Textual Inversion: ng_deepnegative_v1_75t, easynegative
About Image Reproduction:
Some user said that they can not
SHA256
818E09CC3F2EC9EE38091F8E58C73054730D7E262BD055D84474813F1744BBBF
GhostMix Popularity Trend
Heat score, last 12 months
Heat score
8,839°
This week
▼
0.6%
8,842° then, 8,839° now
This month
▼
2.5%
8,851° then, 8,839° now
Past year
▼
29.3%
8,986° then, 8,839° 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.
+52°
Civitai downloads
7,278 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.
+1,481°
AI Horde images
206,625 images the volunteer AI Horde has generated with this model. Each image counts as one download in the download term: usage weighs like a download.
+78°
Generation sites
10,850 downloads and generation runs of this model's copies on PixAI, Yodayo. Each run counts as one download, and their downloads count like Civitai's; all of it shares the download term.
+622°
Likes
14,067 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.
+65°
Adoption rate
About 6 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 8,839°, 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.
- 1Start 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
- 2Add the downloads.224,753 download-equivalents in all, from Civitai downloads, AI Horde images, Generation sites. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.+52° Civitai downloads+1,481° AI Horde images+78° Generation sites+1,611°8,611°running total
- 3Add the likes.14,067 likes and thumbs up, at half the weight of a download.+622°9,233°running total
- 4Add the adoption rate.About 6 downloads a day right now, measured between two readings, at a quarter of the weight.+65°9,298°running total
- 5Bonus for a full model.A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.+150°9,448°running total
- 6Take off the age.The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.−609°8,839°running total
- =The heat score.Where this model stands on every list of this site. Nothing else adjusts it.8,839°
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.
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2053864451
Size
512x768
Clip skip
2
Prompt
flowers in glasses,solo, <lora:seecolor_20230714052712-000002:1>, (((masterpiece,best quality))),((good structure,Good composition,good atomy)), ((clear, original,beautiful)),
Negative prompt
(((worst quality, low quality))),((text)),id,
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
5
Seed
2592804657
Size
512x512
Clip skip
2
Prompt
(Masterpiece:1.2, high quality), <lora:cat_20230627113759:0.8>, lineart, 1cat, (high angle), <lora:teary:0.7>, full body, (blue| grey cat), inside a cardboard box, yellow cat eyes, looking at viewer, detailed pupils, simple background, white background,
Negative prompt
EasyNegativeV2, bad-hands-5, heart, strips, bad-artist-anime
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2053864449
Size
512x768
Clip skip
2
Prompt
flowers in glasses,solo, <lora:seecolor_20230714052712-000002:1>, (((masterpiece,best quality))),((good structure,Good composition,good atomy)), ((clear, original,beautiful)),
Negative prompt
(((worst quality, low quality))),((text)),id,
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
7
Seed
2267399573
Size
1177x1766
Clip skip
2
Prompt
(masterpiece:1.3),(best quality:1.2),8k,absurdres,unity 8k wallpapper,(extremely detailed:1.3),highestres,highres,Amazing,illustration,beautiful studio soft light,stunningly beautiful,incredibly absurdres,vibrant details,cinematic lighting,moody lighting,pixiv,award-winning, professional, highly detailed,perfect detailed face,
transportation_against_window, solo, short hair, black hair, long sleeves, 1boy, sitting, closed mouth, school uniform, jacket, closed eyes, pink hair, male focus, outdoors, pants, hood, water, black jacket, hoodie, facial mark, black pants, sleeping, hood down, spiked hair, building, partially submerged, reflection, gakuran, undercut, ripples, red hoodie, reflective water,train interior,
<lora:transportation_against_window-40:1> ,<lora:lowRA:0.4>
Negative prompt
EasyNegativeV2,ng_deepnegative_v1_75t, lr,(monochrome:1.2),facial mark, facial tattoo,border,frame,(pantyhose),(low quality,worst quality:1.3),bad artist's work,crossed eyes,signature,watermark,username,text
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2053864450
Size
512x768
Clip skip
2
Prompt
flowers in glasses,solo, <lora:seecolor_20230714052712-000002:1>, (((masterpiece,best quality))),((good structure,Good composition,good atomy)), ((clear, original,beautiful)),
Negative prompt
(((worst quality, low quality))),((text)),id,
Settings
Sampler
Euler a
Steps
30
Guidance
7
Seed
2053864452
Size
512x768
Clip skip
2
Prompt
flowers in glasses,solo, <lora:seecolor_20230714052712-000002:1>, (((masterpiece,best quality))),((good structure,Good composition,good atomy)), ((clear, original,beautiful)),
Negative prompt
(((worst quality, low quality))),((text)),id,
Settings
Sampler
DPM++ 2M Karras
Steps
20
Guidance
7
Seed
848376772
Size
1177x1766
Clip skip
2
Prompt
(masterpiece:1.3),(best quality:1.2),8k,absurdres,unity 8k wallpapper,(extremely detailed:1.3),highestres,highres,Amazing,illustration,beautiful studio soft light,stunningly beautiful,incredibly absurdres,vibrant details,cinematic lighting,moody lighting,pixiv,award-winning, professional, highly detailed,perfect detailed face,
transportation_by_window, 1girl, solo, blush, skirt, brown hair, shirt, black hair, thighhighs, long sleeves, holding, hair between eyes, sitting, school uniform, closed eyes, white shirt, pleated skirt, parted lips, serafuku, signature, miniskirt, black skirt, medium hair, sailor collar, scarf, sweater, white thighhighs, zettai ryouiki, neckerchief, window, phone, sleeping, cardigan, cellphone, light particles, smartphone, red neckerchief, reflection, holding phone, red scarf, snowing, train interior, yellow cardigan
<lora:transportation_by_window-16:0.7>
Negative prompt
EasyNegativeV2,ng_deepnegative_v1_75t, lr,(monochrome:1.2),facial mark, facial tattoo,border,frame,(pantyhose),(low quality,worst quality:1.3),bad artist's work,crossed eyes,signature,watermark,username,text
Settings
Sampler
DPM++ 2M Karras
Steps
25
Guidance
6
Seed
384897898
Size
512x640
Prompt
<lora:luna_kindred_m8:1>, luna kindred, (masterpiece:1.2),(best quality:1.3),ultradetailed,illustration,extremely delicate and beautiful girl, (beautiful detailed eyes:1.3), (beautiful detailed face:1.4), detailed light, illustration, lens flare, light leaks, motion blur, 1girl, standing, arm at side, looking at viewer, medium shot, upper body, blush, light smile, black dress, rose, city skyline, cityscape, urban, rooftop, city lights, night, dark, moon
Negative prompt
(worst quality, low quality:1.4), (ugly:1.3), duplicate, morbid, utilated, lowres, bad anatomy, disfigured, error, (badproportions:1.2), extra digit, fewer digits, cropped, normal quality, jpeg artifacts, signature, watermark, username, blurry, text, error, bad, (censored:1.2), (extra limbs:1.2), clonedface, uncleareyes
Run Locally
How to install
What is ComfyUI? A beginner's guide to nodes, workflows and the first graph
Dec 17, 2025
ghostmix_v20Novae.safetensors
Downloads are served by Civitai. Some creators ask for a Civitai login first.
GhostMix is a base model for the Stable Diffusion 1.5 family listed on ModelTrends.ai, a read-only catalog of open source AI image, video and text models. Compare it with other Stable Diffusion 1.5 models, check its heat score to see how it is trending, and open it on PirateDiffusion or BitVector to try it.
More Stable Diffusion 1.5 modelsMore Stable Diffusion 1.5 Base Modelsanimeroboticsci-fiartstylesbasephotorealisticfemalebase model
Browse by Model Family
Text / LLM Models
434
Anima Models
528
Chroma Models
19
Fibo Models
2
Flux Models
1,496
Flux 2 / Klein Models
1,239
Flux 3 Models
3
Moss Models
3
Iris Models
1
MiniMax H3 Models
364
Hunyuan Models
204
Ideogram Models
20
Krea2 Models
717
Qwen Models
20
Qwen2 Models
47
Ltx2 Models
153