A cursed knight clad in intricately detailed dark armor, holding a sword radiating red energy, standing amid ancient ruins with red shadow tendrils swirling behind.
A stunning fantasy woman with long black hair and purple eyes wearing a medieval black outfit stands outdoors with a large castle and snow-capped mountains in the background under clear skies.
AI generated image using Stable Diffusion of a cyberpunk female warrior with silver hair and cybernetic armor standing in a futuristic city.
AI generated image using stable diffusion depicting a cyberpunk woman with blue eyes, short black hair, wearing a futuristic black and purple outfit with a gas mask, standing in a neon-lit city street.
A fantasy princess with bright blue eyes and colorful hair, adorned with intricate gold jewelry and surrounded by a mystical aura. This is an AI generated image using Stable Diffusion.
A vibrant city street adorned with festive decorations, created using Stable Diffusion AI.
AI generated image using Stable Diffusion depicting a cyberpunk forest nymph with futuristic armor, bioluminescent elements, and nature-inspired mech headgear.
A lighthouse with bright lights standing tall amid stormy sea waves under a moonlit sky, generated using Stable Diffusion.
AI-generated image of a woman with blue eyes and short hair styled in a galactic theme using Stable Diffusion.
A close-up of an AI generated cyberpunk girl with blue eyes and a futuristic sci-fi armor. Neon city background emphasized using Stable Diffusion.
AI generated image of a cyberpunk girl hacker with long blue hair, vivid blue eyes, and a futuristic setting created using Stable Diffusion.
A cybernetic robot with a spherical helmet and glowing lights stands in a dimly lit futuristic environment generated by AI using Stable Diffusion.

Recommended Prompts

1girl

Recommended Negative Prompts

EasyNegative,drawn by bad-artist,sketch by bad-artist-anime,(bad_prompt:0.8),(artist name, signature, watermark:1.4),(ugly:1.2),(worst quality, poor details:1.4),bad-hands-5,badhandv4,blurry,child,loli,kids

EasyNegative, drawn by bad-artist, sketch by bad-artist-anime, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), bad-hands-5, badhandv4, blurry, child, loli, kids

Recommended Parameters

samplers

DPM++ 2M Karras, DPM++ SDE Karras, DPM++ 2M

steps

30

cfg

7

clip skip

2

resolution

512x768, 512x768

Recommended Hires (High-Resolution) Parameters

upscaler

4xUltraSharp, 4x-UltraSharp

upscale

2

steps

15

denoising strength

0.5 - 0.6

Tips

Try, experiment, enjoy!

Generate 5 pictures first to identify obvious problems, then create 10-20 more and choose the best for upscaling.

Higher denoising strength increases detail but raises risk of artifacts.

Use ADetailer with face_yolov8.pt and mediapipe_face_mesh_eyes_only models for enhanced facial details.

My models are just a mix of everything that you yourself can find on this wonderful site. I'm not chasing fame, I don't need your money, I just sometimes spend a few hours of my free time experimenting with my favorite models. The page with this model exists on this site only because once my friends asked me to share their mix. And because it's just damn convenient. Please don't accuse me of stealing someone's property. Considering what we're all doing here, that's a little ironic. In my mixes, I use such checkpoints as Luma, RevAnim, DDosmix, Perfect World, GalenaRedux, DarkSushi, CosmicBabes and so on. I don't even remember all the model names. I don't do anything that you can't do yourself.

Try, experiment, enjoy!

Here is the workflow for my pictures:

  1. Sampler: DPM++ 2M Karras (because it runs faster on my weaker hardware, while giving a good result)

  2. Base image size: 512x768 (because I don't have enough VRAM for more).

  3. CFG Scale - 7. Steps - 30.

  4. Default negative line: EasyNegative, drawn by bad-artist, sketch by bad-artist-anime, (bad_prompt:0.8), (artist name, signature, watermark:1.4), (ugly:1.2), (worst quality, poor details:1.4), bad-hands-5, badhandv4, blurry, child, loli, kids

Then I generate 5 pictures to identify any obvious problems, after that I make another 10-20 pictures, choose the best one from them and proceed to the upscaling stage.

  1. I turn on the option Hires.fix

  2. Upscale by - 2 (because I don't have enough VRAM for more)

  3. Upscaler - 4xUltraSharp

  4. Haires steps - 15 (half of the steps from the first stage)

  5. Denoising strength - from 0.3 to 0.6 (the larger this value, the more detailed the picture will be, but the greater the risk of getting artifacts and distortions in those places that the neural network considers doubtful or incomprehensible)

  6. Turn on ADetailer. The 1st is - face_yolov8.pt, the 2nd is the mediapipe_face_mesh_eyes_only. If necessary, I fill in its positive and negative lines, but more often this is simply not necessary.

  7. PROFIT!

Previous
Shuttle 3 Diffusion - fp8
Next
Smeagol from Lords of the Ring, Flux.1 D LoRA - v1.0

Model Details

Model type

Checkpoint

Base model

SD 1.5

Model version

v4.1

Model hash

6d6e223662

Creator

Discussion

Please log in to leave a comment.

Images by DarkSun - v4.1

base model Images

female Images

futanari Images

nsfw Images

sexy Images