ForRealXL V1.0

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

6,751 downloads · 619 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

AIDigitalMediaAgency

on Civitai

ForReal 1.0 by AIDigitalMediaAgency is the 1.0 non-pony lightning release of the realism / general purpose model, trained on thousands of new images. The early beta versions of this model are also available. There is also a pony variant called PonyForReal by the same creator.

Creator notes

Hello ♥ for whatever reason you want to show me appreciation, you can: ❤️❤️ Special Thanks to Please take a look at their amazing work! Update v1.0: if you see when V0.5 was released, you can imagine how hard it was for me to create a better version that is really better in all areas. This is the result of probably 100 different versions. - more Details - better colors at low cfg - better faces (and more variance) (not perfect) For people and faces, you should not use DDPM. Use DPM++ 3M SDE or Euler Update v0.5: Small improvements - better skin, teeth and eyes in humans - more details I am still working on the following improvements - deformed faces / displaced eyes - faces from a distance - xxx Update v0.3: It's just a small update to fix some issues from v0.1. It doesn't change every subject, but some improve. I haven't had a picture in about 1000 pictures where v0.3 wasn't better, so the upgrade is definitely worth it. I can notice the following improvements: - a bit sharper - more realistic - a bit more creative - a bit more possibilities to get nicer hands/faces on full body photos ________________________________________________________________________________ This is a merge of the following Models: Recommended Settings: Sampling Method: DDPM (my absolute favorite), Euler, DPM ++ 3M SDE Sampling Steps: 10 (more very rarely make a difference.) CFG Scale: 1-4 (lower, more realistic, i prefer 1-1.8) Upscaler: SwinIR _4x (this is my all time favorite) (Hires steps: 15; Denoise: 0.28, upscale by 1.5 - 4 (depends on your GPU)) 📌 USE All Images generated in SD Forge with Nvidia RTX 4090 Please test other Settings and share with the communty, so i will learn about the Settings and can optimize. Recommended Loras: Please experiment with the weights. Loras are really gamechanging in this Model! TESTS Here you can find and download my tests: Thank you so much for using this Model. Hope you are get insane results and create some BANGERZ ♥

SHA256

FF0240DDF7486CD2D3D20179221D34AEDCF6C3842EBF7AF4644CDB6D43342F94

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

Also ranked: #443 Hottest AI model · #40 Hottest Stable Diffusion XL 1.0 base model

Not this creator?

Get your own badge

ForRealXL V1.0 Popularity Trend

Heat score, last 12 months

Heat score

8,221°

This week

▲

0.3%

8,222° then, 8,221° now

This month

▲

1.2%

8,226° then, 8,221° now

Past year

▲

28.3%

8,252° then, 8,221° 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.

+1,149°

Civitai downloads

6,751 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.

+419°

Likes

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

+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 8,221°, 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.
6,751 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.
+1,149°
8,149°
running total
3
Add the likes.
619 likes and thumbs up, at half the weight of a download.
+419°
8,568°
running total
4
Bonus for a full model.
A checkpoint carries the weights themselves; add-ons do not outrank one of equal popularity.
+150°
8,718°
running total
5
Take off the age.
The SDXL weights came out in 2023: 150° a year, up to 750°, growing until then.
−497°
8,221°
running total
=
The heat score.
Where this model stands on every list of this site. Nothing else adjusts it.
8,221°

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 LordTerror on

Settings

Sampler

Euler a

Steps

Guidance

1.5

Seed

1156582717

Size

1024x1024

Prompt

by Joe Madureira and Johan Messely in the style of Peter Holme III, silhouette <lora:silhouette:2.00>

Negative prompt

poorly drawn, deviant, mess, low quality, deformed, unprofessional, plastic doll

Render by FradyPriva on

Settings

Steps

Guidance

Seed

1658975633

Size

1792x2560

Prompt

flux-style, detailemaximizer, max details,Photo,realistic,product photo Surreal landscape with floating islands and giant flowers, bizarrely shaped flowers, unreal sky colors, sea of clouds below, dreamlike atmosphere, vibrant colors, detailed, hyperrealistic, 8k

Render by alerus1995 on

Render by Pinkielicious on Civitai

Settings

Sampler

Euler A Turbo

Steps

Guidance

1.5

Seed

2294362797

Size

576x832

Clip skip

Prompt

(vector art style:1.3), Portrait of an angry (hyperrealistic blue hour shot of night shot of hyper-detailed, beautifully color-coded, hyper photorealistic style light and space style night shot of exaggerated features, hyper-detailed, beautifully color-coded, ethereal Hornbill, 8k, buceros :: intricate details, ornate, flowery, bright colors background, peaceful, detailed illustration, octane render :: Johanna Rupprecht style, William Morris style :: trending on artstation, masterpiece, best quality, realistic, very clear insane details, intricate details, beautifully color graded, insanely detailed and intricate, hypermaximalist, elegant, hyper realistic, super detailed, cinematic, highly detailed, {prompt], intricate, sharp focus, elegant, symmetry, perfect, fine, artistic, color spread, enhanced, dynamic composition, creative, ambient atmosphere, professional, glowing, radiant, vivid, beautiful, deep, determined,,, rich, striking, full, incredible, epic, thought, glorious, breathtaking, novel, scenic, amazing, singular, humorous interpretation, big head, big eyes, playful colors, satirical tone. Dark, lit, moody, mysterious. perceptual phenomena, immersive, minimal, detailed, sharp focus. Expressive, impasto, swirling brushwork, vibrant, "realistic, Poster design style, poster art, visually striking and informative poster, professional-grade execution, poster graphic design, (rough brush strokes: 1.5), [soft impressionist brush strokes:1.2], blinding light, canvas texture, muted colors, by Brent Heighton, by Richard Schmid, Cartoon watercolor painting style, playful cartoon character, dynamic composition, whimsical expression, soft and fluid texture, adds charm and personality, subtle gradients and blending, captures light and atmosphere, creates soft and dreamy scenes, watercolor texture, cartoon art style, whimsical character, exaggerated features, vibrant colors, dynamic composition, expressive pose, professional-grade finish, adds humor and charm. anime style, key visual, vibrant, studio anime, highly detailed, great decorative detail, polished, complex, iconic, illustrious, balanced, shiny, fabulous, brilliant, dazzling, excellent, spiritual surreal, fantastic, shining, flawless, delicate, precious, extremely, masterpiece, best quality, realistic, very clear insane details, intricate details, beautifully color graded, insanely detailed and intricate, hypermaximalist, elegant, hyper realistic, super detailed. Dark, lit, moody, mysterious, sharp focus, Poster design style, poster art, visually striking and informative poster, professional-grade execution, poster graphic design, (rough brush strokes: 1.5), [soft impressionist brush strokes:1.2], blinding light, canvas texture, muted colors, by Brent Heighton, by Richard Schmid, Cartoon watercolor painting style, playful cartoon character, dynamic composition, whimsical expression, soft and fluid texture, adds charm and personality, subtle gradients and blending, captures light and atmosphere, creates soft and dreamy scenes, watercolor texture. Cool light, twilight, peaceful, moody, Japanese illustration, kawaii culture, soft textures, pastel colors, character art, anime influences, whimsical designs, cute characters, playful scenes, digital art, vibrant illustrations, pop aesthetics, fashion elements, youthful themes, light-hearted narratives, manga style, expressive faces, contemporary Japanese art, visual charm, cultural motifs . photorealistic, extreme detail, lifelike, crisp, precise,blurry) with open mouth, (Flat style:1.5), flat background, artstation, (sticker:0.4)

Negative prompt

(deformed, distorted, disfigured:1.3), stacked torsos, totem pole, poorly drawn, bad anatomy, wrong anatomy, extra limb, missing limb, floating limbs, (mutated hands and fingers:1.4), disconnected limbs, mutation, mutated, ugly, disgusting, blurry, amputation, 3d, cartoon, anime, sketches, (worst quality:2), (low quality:2), daytime, bright, cheerful, clear, signature, watermark, ugly, off-center, deformed, cropped, frame, worst quality, low quality, lowres, JPEG artifacts, signature, watermark, photo, photorealistic, realism, ugly, off-center, deformed, 35mm film, dslr, cropped, frame, worst quality, low quality, lowres, JPEG artifacts, midday, harsh light, chaotic, flat, (worst quality, low quality, normal quality, lowres, low details, oversaturated, undersaturated, overexposed, underexposed, 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, (bad hands, bad anatomy, bad body, bad face, bad teeth, bad arms, bad legs, deformities:1.3), dark horror, photorealism, western comic style, muted earth tones, abstract, unrealistic lighting, flat shadows, cartoonish features, lack of texture, oversimplification, missing reflections, no depth of field, visible brush strokes, painted effect, subject not centered, important parts cropped out, composition not balanced

No prompt was shared with this render.

Render by LordTerror on

Render by EsheAI on Civitai

Settings

Sampler

Euler a

Steps

Guidance

1.5

Seed

855553731

Size

1024x1024

Prompt

by Junji Ito and John Baizley in the style of Armand Guillaumin, oil painting <lora:oil_painting_envy_anime:0.60>

Negative prompt

poorly drawn, deviant, mess, low quality, deformed, unprofessional, plastic doll

No prompt was shared with this render.

Render by LordTerror on

Settings

Sampler

Euler a

Steps

Guidance

1.5

Seed

3483561982

Size

768x1152

Prompt

by Robert Bissell and Patrick McHale

Negative prompt

poorly drawn, deviant, mess, low quality, deformed, unprofessional, mangled hands, splotchy, weird clothes, plastic doll

Render by LordTerror on

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

Settings

Sampler

Euler a

Steps

Guidance

1.5

Seed

1735622944

Size

768x1152

Prompt

by Pascale Campion and Daniel Merriam in the style of Hayao Miyazaki and Ed Mell

Negative prompt

poorly drawn, deviant, mess, low quality, deformed, unprofessional

Run Locally

How to install

Dec 17, 2025

Open Civitai Download

forrealxlV10_v10.safetensors

12.92 GB · SafeTensor · fp32 · full

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

More by this creator

F.2 Midjourney V6.1 meets FLUX [+ILLUSTRIOUS / SDXL] FLUX v0.5

FLUX

F.2 Midjourney V6.1 meets FLUX [+ILLUSTRIOUS / SDXL] ILLUSTRIOUS v0.5

FLUX 2 / KLEIN

FLUX Image Upgrader / Detail Maximizer / Contrast Fix for low CFG [+ILLUSTRIOUS / SDXL / SD 1.5] FLUX v0.1

All models by AIDigitalMediaAgency

BASE

Similar Models

fullyreal4

BASE

satanichia kurumizawa

anna daily lives

Creepy Cute Magical Refined