A young anime girl in a fighting stance sitting cross-legged, wearing black yoga pants, a black sporty crop top with an orange band, white sneakers, and jewelry including earrings, a necklace, and a choker.

Recommended Negative Prompts

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist

Recommended Parameters

samplers

Euler a, DPM2 Karras

steps

9 - 50

cfg

1.5 - 9

resolution

704x1024

Recommended Hires (High-Resolution) Parameters

upscaler

nmkdSiaxCX_200k, ESRGAN_4x, SwinIR 4x, R-ESRGAN 4x+ Anime6B

upscale

2

steps

30

denoising strength

0.05 - 0.3

Tips

If sampling steps are lower than 9, important details will be lost, and if higher, redundant details appear.

Lower CFG scale than 1.5 results in less accuracy, sharpness, and vivid colors; higher causes spots and color errors.

Use ADetailer default settings but adjust inpaint width and height to 1024 for the sdxl model.

For hires fix, nmkdSiaxCX_200k or ESRGAN_4x retain small details with less distortion; SwinIR 4x gives sharper results but may distort fine details.

Keep denoising strength below 0.2 for hires fix to avoid image errors.

FreeU is adjusted for SDXL model with default parameters.

Creator Sponsors

I created a youtube channel specializing in AI-made songs: https://youtube.com/@duchaiten?si=o3GZZ3aODRafPKUH

Support me via PayPal: http://paypal.me/duchaiten and Patreon: https://linktr.ee/Duc_Haiten

To create unlimited images at low cost without installation, try mage.space, hosting some exclusive models.

I just added a TCD model. This is a model created to produce quality pictures close to v2.0 but with only 9 steps, I chose TCD instead of lightning because it is a more realistic model.

I wrote the wrong model name in the sample photo when I left it as v1.0

Some notes when using the TCD model:

Sampling method: Euler a (You can try other sampling methods, but most of them are unusable)

Sampling steps: 9 (If it is lower, it will lack important details, but if it is higher, redundant details will appear)

CFG Scale: 1,5 (Lower will not have enough accuracy or sharpness or vivid colors in the image, and anything higher will cause spots and color errors to appear)

Negative prompt: (This doesn't have to be the same as mine, perhaps yours might be even better.)

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist


Please note, the sample images above are indeed from the model, but they have been used with specific settings, and added extensions on automatic1111 such as hires fix, freeU, ADetailer. If you want to get the closest results, please stick to the information obtained from the sample photos, or follow the instructions at the bottom of the article.


This second version has made some minor adjustments to the NSFW 3D-style data, the most significant changes in this version lie in the data of different art styles, along with the textual dataset within the model. I want it to become more comprehensive and expansive, but it will still focus on NSFW 3D unreal. When compared, you will see it produces images with higher flexibility, more diversity, smoother body lines and facial contours, more user-friendly with some manga and anime keywords, along with other art styles, the hands have also improved compared to v1.0. However, please note that although there is a considerable amount of data, it is still a fine-tuning model, so there will be a lot of data not yet added. If you enter a prompt that falls into the results not included in the data I trained into the model, it will revert to the original data of the base model and the results might not look good.

I created a youtube channel specializing in posting songs made from AI. If anyone is interested, you can try visiting:

https://youtube.com/@duchaiten?si=o3GZZ3aODRafPKUH

If you like my content, support me at:

http://paypal.me/duchaiten

Patreon
in here:
https://linktr.ee/Duc_Haiten

If
you want to use my models to create unlimited images at a small cost without having to install anything, mage.space will be a good choice, i have some models that are exclusively available on there.


The priority settings for this model are:

Sampling method - DPM2 Karras.

Leave ADetailer at default and only adjust the inpaint width and inpaint height to 1024 since you are using the sdxl model.

For Hires.fix, use nmkdSiaxCX_200k or ESRGAN_4x, it will result in blurrier outcomes compared to other hires fix models but it helps retain small details such as skin, hair strands, water droplets, and muscle lines...etc without distortion.

You could also use the hires fix model SwinIR 4x if you want it sharper, but some small details will be distorted and hard to preserve. Also note that the Denoising strength of hires fix should not exceed 0.2, otherwise, some errors in the images may occur.

As for FreeU, I have switched it to be suitable for SDXL and kept the default parameters.

Negative prompt:

(worst quality:1.5), (low quality:1.5), (normal quality:1.5), lowres, bad anatomy, bad hands, multiple eyebrow, (cropped), extra limb, missing limbs, deformed hands, long neck, long body, (bad hands), signature, username, artist name, conjoined fingers, deformed fingers, ugly eyes, imperfect eyes, skewed eyes, unnatural face, unnatural body, error, painting by bad-artist

Previous
GLaDOS - Portal [SD 1.5/PonyXL/Illustrious] - V1 Illustrious
Next
Ivan Shishkin - V1

Model Details

Model type

Checkpoint

Base model

SDXL 1.0

Model version

v0.16

Model hash

88b85503f9

Creator

Discussion

Please log in to leave a comment.

Images by DucHaiten-Real3D-NSFW-XL - v0.16

A young anime girl in a fighting stance sitting cross-legged, wearing black yoga pants, a black sporty crop top with an orange band, white sneakers, and jewelry including earrings, a necklace, and a choker.

3d Images

3D rendered muscular woman with freckles and black hair in a shiny plugsuit, posing against a simple red background with cinematic lighting and atompunk style.
Close-up photorealistic portrait of a stylish hipster girl with dark makeup, defined jawline, and an alluring necklace.
3D realistic image of Tifa Lockhart sitting with one leg up wearing a white sports bra and black sweatpants, showing shiny skin and sweat on a simple white background.
A highly detailed turtle wearing a jetpack, flying above a vibrant city canal surrounded by colorful buildings under a blue sky.
A vibrant yellow classic car speeding on a wet urban street with a large explosion in the background under a cloudy sky.
Loona from Helluva Boss sitting in a gaming chair with sad big red eyes, holding a flaming sign saying 'Need Buzz to generate more Loona' inside a gaming room.
Compact futuristic bedroom with metallic and industrial design, featuring a messy bed near a large panoramic window overlooking a neon-lit cyberpunk city skyline at night.
A photorealistic image of a stylish woman in a striking red dress and sunglasses, standing confidently in an airport terminal surrounded by a towering, chaotic pile of colorful suitcases on a baggage cart.
A realistic 3D moth girl with split black and white hair, wide red eyes, and an awestruck expression with drool, leaning over a glowing light bulb on a wooden table.
A 3D rendered medieval female arbalist with braided brown hair, brown eyes, wearing light brown medieval clothing and leather armor, holding a crossbow with a serious sideways glance.

base model Images

Photorealistic scene of undead characters including zombies and skeletons walking through a spooky cemetery illuminated by glowing jack-o'-lanterns under a dark, ominous sky.

game character Images

AI generated image using stable diffusion of a young woman with intense expression, wearing a blue outfit with a harness, ready for an adventure.
AI-generated image of an anime character in a fantasy forest using stable diffusion
Warrior female with braided hair, wearing medieval armor and holding a sword, AI generated image using Stable Diffusion.
A highly realistic AI-generated image of a fantasy dwarf character with a thick beard and pointed ears, dressed in a leather and cloth outfit, leaning on a moss-covered tree in an enchanted forest created using Stable Diffusion.

sexy Images

A stylized anime girl with long black hair and striking green eyes, wearing a black outfit and thigh-high stockings adorned with red flowers tattoo, holding a katana against a red background.
A beautiful elf girl with long blonde hair, green eyes, and pointed ears in a magical forest setting, wearing detailed green and gold clothing with a crown.
Red blood dripping in a flat design style with a minimalist inverted background, featuring smooth glossy textures and spot color highlights.
Silhouette of a seductive blood sorceress in glossy red against a muted gray background with flat design and neon highlights.
Detailed side profile of a tribal prehistoric dinosaur adorned with vibrant orange and black ornate feathers and decorations in a flat color style with an inverted background.
A silver-haired fairy wearing a green tight dress and a tiara, standing in a mystical forest under the full moon with glowing yellow wings and pixies surrounding her.
A flat-design style illustration of a mermaid floating underwater, featuring intricate fractal patterns in orange against a dark inverted background with pearlescent and neon effects.
Silhouetted goddess of sin with neon orange fractal tendrils radiating from her head against a dark inverted background in a flat, lineart-free style
Portrait of a seductive goddess of flowers adorned with bright red floral headpieces and intricate jewelry, featuring flat colors and triadic color scheme with green background.
A fierce Amazon warrior with white braided hair in detailed bronze armor, holding a trident and an axe, standing in ancient stone ruins with volumetric lighting.

woman Images

A silver-haired elf woman wearing futuristic armor stands against a swirling, colorful sky with clouds, depicted in a vivid cyberpunk oil painting style.
Animated portrait of Lois Lane wearing a purple suit jacket and black skirt standing on an urban street with skyscrapers in the background, holding a purple handbag and smiling.
Full-body portrait of a woman with freckles and long ginger hair wearing a vibrant multicolored flowing gown in shades of orange, purple, and blue.
A woman holding a lit candle with a pitch black dark background illuminating half of her face with warm candlelight.
Portrait of a woman with platinum blonde hair and purple eyes, wearing a black off-shoulder crop top, standing against a yellowish-brown textured wall, showing a tattoo on her upper arm and a toned physique.
3D rendered muscular woman with freckles and black hair in a shiny plugsuit, posing against a simple red background with cinematic lighting and atompunk style.
Close-up portrait of a woman with green eyes lying on a bed, illuminated by warm golden hour sunlight indoors.
Close-up portrait of a woman with medium messy hair and warm light on her lips, framed by a vintage window with a partial shadow and Eiffel Tower reflection.
Anime-style woman with green snake hair sitting on blue office chair at her desk, wearing business attire and black high heels.
A woman resembling Medusa with green snakes as hair, wearing glasses and a red dress, waving at the viewer with large green eyes.