Stable Diffusion WEBUI/Automatic1111 & Forge [Image Generation]

Overview

This guide shows how to generate images similar to mine using my Illustrious XL models and the WAI-NSFW checkpoint in Automatic1111 & Forge.

⚙️ Core Settings

Steps: 20-30

Use 20–24 for faster drafts, and 26–30 for final renders when you want more polish and definition.

Sampler: Euler a

A stable and fast baseline sampler, ideal for detailed prompts and character-focused compositions.

Schedule Type: Automatic

Lets the interface choose the best scheduler behavior for your selected sampler.

CFG Scale: 5-7

Lower values (4–5) give more freedom and creative variation.

Higher values (6–7) enforce the prompt more strictly, but may cause oversaturation or stiffness.

🧩 Model & Precision

Model/Checkpoint: WAI-NSFW-illustrious-SDXL (v16).

Clip Skip: 2

Common in anime and merged-style models. It emphasizes the main subject and keeps outlines clean. If you are getting bad results with Forge try to set it at 1.

ENSD: 31337

Ensures consistent behavior across multiple sessions and tests.

Token Merging Ratio: 0.5

Speeds up generation by merging less-important tokens. If you notice detail loss or visual drift, reduce it to 0.25 or disable it completely.

VAE: Not needed, already embedded in the model/checkpoint

Specifies the active VAE (Variational Autoencoder) used for color space and tonal compression.

👤 ADetailer - Face (2nd Pass)

Detector Model: face_yolov8n.pt

Confidence: 0.3

Dilate/Erode: 4

Mask Blur: 12

Higher blur is necessary for HiRes Fix to prevent visible square artifacts along mask edges.

Denoising Strength: 0.55

Stronger denoising ensures the face is fully refined after upscaling. Lower values only work on low-res or non-HiRes renders.

Inpaint Only Masked: True

Restricts edits to the face area, preserving the rest of the image.

Inpaint Padding: 32

Purpose: Provides gentle, localized facial refinement, improving facial definition without altering lighting, color balance, or the overall composition.

⚠️ Important Note (Very Common Mistake):
Applying ADetailer on the 1st pass can unintentionally change identity-defining features such as:

• Eye color

• Facial expression

• Face shape

Always use ADetailer after the base and HiRes pass to maintain correct character identity.

🆙 HiRes Settings

HiRes Upscale: 1.5

Upscales the image to 150% of its original resolution. Use 1.5x for a moderate resolution boost that enhances details without excessive VRAM usage.

HiRes Steps: 20

Defines the number of steps during upscaling. 20 steps offer a good balance between quality and processing time, improving detail while avoiding excessive rendering time.

HiRes Upscaler: R-ESRGAN 4x+ Anime6B

An upscaler designed for anime-style images, perfect for enhancing details while keeping clean lines. Ideal for illustrations, not recommended for photo-realistic images.

Denoising Strength: 0.35-0.5

Controls noise removal during upscaling. Set between 0.35–0.5 to remove noise while preserving details, use 0.4 for a balanced result.

Higher HiRes upscaling increases the need for stronger Mask Blur and Denoising in ADetailer to prevent face squares.

>_ Prompt Recommendations

This is my suggested structure for building a prompt on civitai:

1. Quality Tags

   • Focus on tags like masterpiece, best quality, and amazing quality to set the desired level of detail and artistic quality.

2. Character Type & Number

   • Specify whether you want a single character (e.g., 1girl, 1boy) or multiple characters. If there are multiple characters, you can also indicate the number of characters (e.g., 2girls).

3. Trigger Word

   • This is used to activate the lora.

4. Character Details

   • Include specific attributes like hair color, eye color, personality, or specific features (e.g., blonde hair, red eyes, long hair, medium breasts, etc.).

5. Clothing & Outfit

   • Describe the character’s clothing in detail, including colors, fabrics, and specific items like white shirt, red skirt, sneakers, or armor.

6. Pose & View/Camera Position

   • Specify the character's pose (e.g., standing, sitting, jumping) and camera angle (e.g., front view, side view, overhead view). This is essential for guiding the composition of the image.

7. Background & Illumination Details

   • Define the background style (e.g., white background, simple background, urban setting, nature) and include lighting conditions (e.g., soft lighting, backlighting, sunset). This helps set the mood and atmosphere of the scene.

🚫 Negative Prompt Recommendations

NO NSFW Negative Prompt

bad quality, worst quality, worst detail, sketch:1.2, ((watermark, text, logo, signature, artist name, name, labels, artist signaure)), guro, futa, futanari, femboy, nude, naked, nsfw, suggestive, lewd, wardrobe malfunction, sheer clothing, see-through, skirt lift, exposed, exposed breasts, exposed nipples, exposed pussy, see-through clothing, transparent clothing, cameltoe, nipples, nipple bulge, testicles, penis, pussy, colored outline:1.2, bad hands:1.2, bad anatomy:1.2, malformed body:1.2, fused body parts:1.2, multiple navels:1.2, double navels:1.2, extra navel:1.2, ((baby face:1.2, youthful:1.2, young:1.2))

NSFW Negative Prompt

bad quality, worst quality, worst detail, sketch:1.2, ((watermark, text, logo, signature, artist name, name, labels, artist signaure)), censor, mosaic censoring, bad hands:1.2, bad anatomy:1.2, malformed body:1.2, fused body parts:1.2, futa, futanari, multiple navels:1.2, double navels:1.2, extra navel:1.2, ((baby face:1.2, youthful:1.2, young:1.2))

📌 Additional Notes & Tips

This is not a final or exhaustive guide, please feel free to experiment and share suggestions to help improve it. Thank you.