Chilloutmix

9337°

#asian #realistic #semi-real #base #porn #sex

NSFW

NSFW model. Its pictures are hidden while NSFW is off; turn NSFW on to see them.

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.

Rent a GPU on the cloud

Graydient Cloud GPU

Unlimited · flat fee

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.

Chilloutmix V2 (NI) by Tasuku2023 is best known as an "asian beauty" ai model. It works best with the Pure Eros Face textual inversion embeddings and character loras like Japan Doll and Taiwan Doll

Creator notes

*I modified the License.(22/2/Feb) That is not usual "creativeml-openrail-m" Check Permission and Liscense below(modified Dreamlike Liscense.) When I made samples, My eta (see setting) was "0". And ESND was "1" Now,I canged them to eta to "0.67" and ESND "31337"(20/Feb/2023) よいこのみんなは節度を守って楽しもうな！！職場や家族の前で開くのはやめておいたほうがいいよ！！当モデルを転売することは認めていません。生成された画像の取り扱いには、自己責任の上、十分注意してください。当モデルを使用したことを明記せずに生成された画像を公開することは禁止です。商用利用は一切認めていません。 AIコミュニティの発展に悪影響を与えるような行動や個人の権利やプライバシーを侵害するような利用は禁止します。 New merge model for 2.5D illustration here!! ↑ (少しイラスト寄りにしたのもあります。) IMPORTANT:First of all, I never suggest regenerate images of “real “person, but, photo "realistic" images. 本人郑重声明：本模型原则上禁止用于训练基于明星、公众人物肖像的风格模型训练，因为这会带来争议，对AI社区的发展造成不良的负面影响。如各位一定要违反以上声明训练相关模型并公开发布，请在您的发布说明中删除与本模型有关的一切描述。感谢各位使用者的支持与理解。 I solemnly declare: In principle, this model is prohibited from being used for training style models based on portraits of celebrities and public figures, because it will cause controversy and have a negative impact on the development of the AI community. If you must violate the above statement to train the relevant model and release it publicly, please delete all descriptions related to this model in your release notes. Thank you for your support and understanding. I appreciate you enjoy my model. But, it might cause legal conflicts if you made some works/Loras/Embeddings named with actual person/copyright. I beg you never to put them with my model. If you can't be with actual name/copyright, just remove my model from your works. I never suggest to regenerate actual persons/copyright with my models. And I never want any legal conflicts from my models. PLEASE!! Care about legal conscious and privacy!! Show what your favorite works from this merge on comments, if you like this mix. I wanna see and share your good ideas from this merge. :) It’s my pleasure. Let's share your good ideas and enjoy this merge!! (Some funs have already put their great works from this merge. It could be like a kind of community.) I started to put some tips with samples/prompts on review. Try to find them!!(I've already put 5. 14/Feb/2023) (I'm sorry but I stop to invite my discord.) Konnichiwa!!!! ・This is Merged "Basilmix"( + wonderful realistic models. ( by ) ・Use: vae-ft-mse-840000（←！！） ) 1. Get vae-ft-mse-840000-ema-pruned.safetensor 2. Put it in folder(models>VAE) 3. Set VAE on webUI(Settings>Stable diffusion>SD VAE) 4. Don't forget to push "Apply settings" (Your picture would be foggy, if you didnt use vae with this merge.) You dont need to use VAE with the latest ver."Chilloutmix-Ni" ・All sample images have been upscaled using highrexfix And, I made some samples when I made test ckpt file for myself. I made safetensor file after that. (Cuz, ckpt files couldnt be liked on this site, because they include arbitrary code.) That’s why Prompts from some sample pictures wouldn't make the same pictures,sorry. ・I think this model is not perfect, but better for realistic Asian(+ other areas.Just try) . ・Face variation is really limited. Use LORA or Embeddings as you like.(←！！) I like to use "Ulzzang-6500" embeddings (I used that for all sample images). This is my type....I couldn't avoid generating with this.... You can get it here. (Thanks and for telling me on comments.) ↓ (all 3 adress are the same files) Other Embeddings By By Dcy:Asian face mix (Thanks for sharing !!) As the same as other areas of this world, Asian are quite variated and there are quite lots of races, communities and nations in Asia. Who can tell you what is the typical Asian? '"Typical "could cause less variation. I've been coming to think face variation should be developed not on models, but on LORAs and also on embeddings. Because,results can be quite randomed if that was developed on models. (Yeah,I know random encounting could be also fun,though.) You can make ideal faces with LORAs, embeddings as you like. (Some examples of face variation by using some TI/HN/LORA) Some Lora could work very nice, even though they were made for 2D charas. They are notable that 2D charas Loras generate not only crothes, hair styles, but also facial features!! This model is likely to get bigger tits. If you like more smaller tits, try both of prompts, "(small breasts) and (fantasy breasts)" (Slim girl) maybe good. ・Preparing: I put explanation too much,sorry. ーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーーー Due to using , this model has the following license: Modified License（Dreamlike photoreal allowed me to modify Liscence.） This model is licesed under a modified CreativeML OpenRAIL-M license. - You can't host or use the model or its derivatives on websites/apps/etc., from which you earn, will earn, or plan to earn revenue or donations. If you want to, please email us at - You are free to host the model card and files (Without any actual inference or finetuning) on both commercial and non-commercial websites/apps/etc. Please state the full model name (Dreamlike Diffusion 1.0) and include a link to the model card ( - You are free to host the model or its derivatives on completely non-commercial websites/apps/etc (Meaning you are not getting ANY revenue or donations). Please state the full model name (Dreamlike Diffusion 1.0) and include a link to the model card ( - You are free to use the outputs of the model or the outputs of the model's derivatives for commercial purposes in teams of 10 or less （Edit:We sencerely ban to use the outputs of the model or the outputs of the model's derivatives(further murged models and Loras included) for commercial purposes. Because, it would cause controversy and have a negative impact on the development of the AI community, wheter images were generated from real person or not.） - You can't use the model to deliberately produce nor share illegal or harmful outputs or content - The authors claims no rights on the outputs you generate, you are free to use them and are accountable

921,073 downloads · 73,707 likes on Civitai

SHA256

FC2511737A54C5E80B89AB03E0AB4B98D051AB187F92860F3CD664DC9D08B271

chilloutmix Popularity Trend

Heat score, last 12 months

Heat score

9,337°

This week

▼

0.6%

9,340° then, 9,337° now

This month

▼

2.5%

9,349° then, 9,337° now

Past year

▼

29.7%

9,486° then, 9,337° 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.

+693°

Civitai downloads

921,073 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.

+11°

Torrent seeders

15 people keep serving the weights over torrents or hosted mirrors. Serving a file costs real bandwidth and says the weights are still wanted, so each seeder counts as 1,000 downloads in the download term.

+1,241°

AI Horde images

1,620,229 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.

+730°

Likes

73,707 likes and thumbs up across the sources. A like weighs half a download, on the same log scale.

+121°

Adoption rate

About 40 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 9,337°, 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.
2,556,302 download-equivalents in all, from Civitai downloads, Torrent seeders, AI Horde images. Ten times the downloads adds the same 300°, so size matters but never runs away with the score.
+693° Civitai downloads
+11° Torrent seeders
+1,241° AI Horde images
+1,945°
8,945°
running total
3
Add the likes.
73,707 likes and thumbs up, at half the weight of a download.
+730°
9,675°
running total
4
Add the adoption rate.
About 40 downloads a day right now, measured between two readings, at a quarter of the weight.
+121°
9,796°
running total
5
Bonus for a full model.
A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.
+150°
9,946°
running total
6
Take off the age.
The SD15 weights came out in 2022: 150° a year, up to 750°, growing until then.
−609°
9,337°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
9,337°

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.