Better faces cultures sdxl/FLUX multifaces v3

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

1,436 downloads · 396 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

sevenof9247

on Civitai

__html__----> left with my lora <----- , , , -----> right without and other steps <-----V........... see below ..............Vtry my other face and makeup lorahttps://civitai.com/models/151594?modelVersionId=175861so carefule, it improves and needs less steps, so play with it ...i want real faces so no symmertrie and natural skin :)ATTENTION -> weight correction 0.3-0.9 results with 25 steps DPM++2M SDE Karras almost the same images as without and 70 stepsTrigger is not essential but useful for the culture ! ;)has a great impact on lower Sampling steps <30if you use DPM++3M SDE Karras with 70…__html__----> left with my lora <----- , , , -----> right without and other steps <-----V........... see below ..............Vtry my other face and makeup lorahttps://civitai.com/models/151594?modelVersionId=175861so carefule, it improves and needs less steps, so play with it ...i want real faces so no symmertrie and natural skin :)ATTENTION -> weight correction 0.3-0.9 results with 25 steps DPM++2M SDE Karras almost the same images as without and 70 stepsTrigger is not essential but useful for the culture ! ;)has a great impact on lower Sampling steps <30if you use DPM++3M SDE Karras with 70 steps, you meight dont need my lora-multifacesv3 -> (group, crowd, many faces), it only generates more people, distant faces are still not so goodweight (0.3-0.8)-multifacesv2 -> (trigger: "number" faces) combine with my v3, try and tell me ;)And please its for the basemodel! so you can try or merge it and finde out ;)i used also copax and juggernaut that is already not that bad at small faces so may you dont need it!-multifacesv1 -> (trigger: group, faces) combine with my v3, try and tell me ;)--> all in all i suggest "Face Editor" or refiner for small faces !-face enhancer_v3 -> more strong in close-ups and pls register my prompts ;)face enhancer_v2 -> much more smother and better ;)please merge in your checkpoint, and tell me, btw i have less trained lorasmore hints below! ->face enhancer(learning: ran on an intel-i7 with an RTX4060, 7 hours with 300 images)its a lora file, so copy in

Creator notes

I found that images generated with my LoRA appear bit more amateur and less like the puppy "model_flux" style. In Better Faces, I aimed to include a diverse range of cultures and ethnicities—15 if I remember correctly—with both young and old subjects, currently focusing on women. aborigines, african, arab, arctic, brazilian, chinese, egyptian, finish, german, havaiian, indian, japanese, mongolian, russian, western my FLUX-lora responds to age prompts like __yo for 20yo, 30yo, 40yo. Weight: start with 0.3 look image post for more, i was curious also negativ has an impact^^ V........... see below ..............V Try my other face expression LoRA. If you use it at a weight of only 0.4 (without trigger words), you'll achieve more realistic results. I aim for realistic faces with natural skin, avoiding perfect symmetry. :) FLUX with Euler-Sampler and SGM-Uniform-Scheduler performs well at -> 15-25 Steps Trigger words aren't essential but are useful for specifying cultural features! and "yo" ;) Model Descriptions: FLUXV3: new image set, new caption, 15 cultures, no permission to merge! FLUX: Recognizes mature (40yo) and young (20yo) subjects with reduced bokeh effect. For higher weights, it learns faces without jewelry, so consider adding jewelry and background details if desired. pony_weak: Better for close-ups; doesn't perform well with complex prompts. Not limited to "1girl" and includes backgrounds. pony_strong: works better with more complex prompts, not only 1girl, and call background face enhancer_v3: Stronger in close-ups. Please consider using my prompts. ;) face enhancer_v2: Much smoother and improved. Multi-Face Models: multifacesv_3: (Keywords: group, crowd, many faces) Generates more people, but distant faces still need improvement. Recommended weight: 0.3-0.8. multifaces_v2: (Trigger: specify the "number" of faces) i used also copax and juggernaut that is already not that bad at small faces so may you dont need it! multifaces_v1 -> (trigger: group, faces) Additional Recommendations: Overall, I suggest using Adetailer or a refiner for enhancing small faces. Face Swap with Adetailer and Reactor The new SDXL VAE (released on 2023.07.26) is significantly better than older versions for face generation. Please try my LoRA, and you'll often get more realistic faces—not those blurred, soft ones. ;) Hints: - please, almost no negative prompt is necessary! see my articles: All SFW!

Trigger words

group of people

crowd

many faces

SHA256

9114385A5475ECE18F92450B4BA5A58CB1F49784D08FDCDD28C3E6E2E21C2A52

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

better faces cultures sdxl/FLUX multifaces v3 Popularity Trend

Heat score, last 12 months

Heat score

7,840°

This week

▲

0.1%

7,842° then, 7,840° now

This month

▲

0.3%

7,847° then, 7,840° now

Past year

n/a

Wasn't released/tracked

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.

+947°

Civitai downloads

1,436 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.

+390°

Likes

396 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 7,840°, 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.
1,436 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.
+947°
7,947°
running total
3
Add the likes.
396 likes and thumbs up, at half the weight of a download.
+390°
8,337°
running total
4
Take off the age.
The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.
−497°
7,840°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
7,840°

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 sevenof9247 on

Civitai

Prompt on BunchaPrompts

Settings

Sampler

DPM++ 3M SDE Karras

Steps

Guidance

Seed

4286732063

Size

1024x680

Prompt

photo of a large group of people in suits and ties sitting in a large concert hall, (many faces),

Negative prompt

painting, drawing, sketch, cartoon, anime, manga, render, watermark, bw, monochrome,

Render by sevenof9247 on

Civitai

Prompt on BunchaPrompts

Settings

Sampler

DPM++ 3M SDE Karras

Steps

Guidance

Seed

498658999

Size

1024x680

Prompt

photo of a large crowd of young people on a demonstration , (many faces),

Negative prompt

painting, drawing, sketch, cartoon, anime, manga, render, watermark, bw, monochrome,

Render by sevenof9247 on

Civitai

Prompt on BunchaPrompts

Render by sevenof9247 on Civitai

Settings

Sampler

DPM++ 3M SDE Karras

Steps

Guidance

Seed

4286732063

Size

1024x680

Prompt

photo of a large group of people sitting in a cinema, many faces,

Negative prompt

painting, drawing, sketch, cartoon, anime, manga, render, watermark, bw, monochrome,

How to install a LoRA: folders, file checks and first use in ComfyUI, Forge, Automatic1111 and Draw Things

Settings

Sampler

DPM++ 3M SDE Karras

Steps

Guidance

Seed

4286732063

Size

1024x680

Prompt

photo of a large group of people in suits and ties sitting in a large concert hall, (many faces), <lora:people_010_cosine_iter4_ 0000025all_jugger_adafactor_128_64_new:0.7>

Negative prompt

painting, drawing, sketch, cartoon, anime, manga, render, watermark, bw, monochrome,

Run Locally

How to install

Sep 24, 2025

Open Civitai Download

multifaces_v3.safetensors

650 MB · SafeTensor

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

More by this creator

better faces cultures sdxl/FLUX cultures_flux_v2

FLUX

Star Trek Ships Enterprise Star Trek v1.4

STABLE DIFFUSION 1.5

Star Trek Ships Enterprise Star Trek v1.3

STABLE DIFFUSION 1.5

All models by sevenof9247

Illustrious XL 1.0

BASE

Atoli .Hack//G.U.

noobevo