Stable Diffusion

[subject], [description], [environment], [style], [quality]

1girl, long hair, blue eyes,
white dress, standing in garden,
detailed background, soft lighting,
masterpiece, best quality, 8k

lowres, bad anatomy, bad hands,
text, error, missing fingers,
extra digit, fewer digits, cropped,
worst quality, low quality,
normal quality, jpeg artifacts,
signature, watermark, username, blurry

(beautiful:1.3)
((important))        # ~1.21x
(((very important))) # ~1.33x

(unwanted:0.7)
[less important]     # ~0.9x

cat AND dog        # Generate both cat and dog

portrait BREAK landscape

512x512   # Default
512x768   # Portrait
768x512   # Landscape

1024x1024 # Default
1024x1536 # Portrait
1536x1024 # Landscape

-1        # Random seed
Fixed     # Reproducible results

Realistic Vision
SDXL Realistic
Juggernaut XL

Anything V5
Counterfeit
Animagine XL

<lora:lora_name:weight>

1girl, <lora:koreanDollLikeness:0.7>,
detailed face, masterpiece

portrait, <lora:styleA:0.6>,
<lora:styleB:0.4>, best quality

(in negative prompt)
EasyNegative, badhandv4, ng_deepnegative

vae-ft-mse-840000
sdxl_vae

Improve colors and details
Reduce grayish appearance

Upscaler: R-ESRGAN 4x+
Hires steps: 10-20
Denoising strength: 0.3-0.5
Upscale by: 1.5-2

Canny         # Edge detection
OpenPose      # Pose control
Depth         # Depth map
Lineart       # Line art
Tile          # Detail enhancement
IP-Adapter    # Image reference

Denoising strength:
0.1-0.3  # Minor changes
0.4-0.6  # Medium changes
0.7-0.9  # Major changes

masterpiece, best quality,
ultra detailed, 8k uhd,
high resolution, intricate details,
sharp focus, photorealistic

worst quality, low quality,
normal quality, lowres,
bad anatomy, bad hands,
text, error, cropped,
jpeg artifacts, signature,
watermark, username

score_9, score_8_up, score_7_up
detailed, masterpiece

score_6, score_5, score_4,
low quality, blurry

Positive:
1girl, solo, portrait, looking at viewer,
[hair color] hair, [hairstyle], [eye color] eyes,
[clothing], detailed face, beautiful eyes,
natural lighting, soft shadows,
masterpiece, best quality, 8k

Negative:
lowres, bad anatomy, bad hands, text,
error, missing fingers, extra digit,
fewer digits, cropped, worst quality,
low quality, normal quality

1girl, solo, portrait, looking at viewer,
blonde hair, long wavy hair, green eyes,
white blouse, detailed face, beautiful eyes,
natural lighting, soft shadows,
masterpiece, best quality, 8k

Positive:
landscape, [scene type],
[time] sky, [weather],
volumetric lighting, atmospheric,
detailed environment, high detail,
masterpiece, best quality, 8k

Negative:
blurry, low quality, text, watermark,
ugly, deformed, oversaturated

landscape, mountain lake at sunset,
orange sky, scattered clouds,
volumetric lighting, atmospheric,
detailed environment, high detail,
masterpiece, best quality, 8k

Positive:
1girl, anime style, [character description],
[clothing], [pose/action],
detailed, vibrant colors,
masterpiece, best quality

Negative:
lowres, bad anatomy, bad hands,
worst quality, low quality,
extra limbs, missing limbs

1girl, anime style, silver hair, red eyes,
black gothic dress, holding umbrella,
standing in rain, detailed, vibrant colors,
masterpiece, best quality

Positive:
product photography, [product],
studio lighting, white background,
professional, commercial,
high detail, 8k uhd

Negative:
blurry, low quality, shadows,
text, watermark, cluttered

old wizard with long white beard,
wearing purple robes with golden stars,
holding glowing staff, magical aura,
fantasy art style, detailed,
dramatic lighting, masterpiece

female warrior in ornate armor,
battle stance, sword drawn,
wind blowing through hair,
epic fantasy, cinematic lighting,
detailed armor, masterpiece, 8k

interior of futuristic space station,
large observation window showing Earth,
clean white surfaces, holographic displays,
sci-fi movie style, cinematic,
volumetric lighting, 8k

advanced humanoid robot,
sleek chrome design, glowing blue eyes,
standing in laboratory,
sci-fi concept art, highly detailed,
studio lighting, 8k

majestic lion in savanna,
golden hour lighting, dramatic sky,
wildlife photography style,
sharp focus, detailed fur,
National Geographic quality

coral reef teeming with tropical fish,
sunlight rays through water,
underwater photography, vivid colors,
sharp focus, detailed, 8k

chocolate lava cake with molten center,
fresh raspberries, mint leaf garnish,
dark slate plate, food photography,
shallow depth of field, studio lighting,
professional, appetizing

bowl of ramen with soft-boiled egg,
steam rising, chopsticks, detailed noodles,
overhead shot, food photography style,
warm lighting, professional, 8k

minimalist living room interior,
floor to ceiling windows, city view,
neutral colors, designer furniture,
architectural photography, natural light,
clean lines, interior design magazine

gothic cathedral interior,
sunlight streaming through stained glass,
stone pillars, vaulted ceiling,
architectural photography, dramatic lighting,
detailed stonework, 8k

Ultimate SD Upscale
Tiled Diffusion
ADetailer (face fix)

Dynamic Prompts
Prompt All-in-one

sd-webui-controlnet

Model: face_yolov8n.pt
Confidence: 0.3
Denoising: 0.4

--medvram           # Medium VRAM
--lowvram           # Low VRAM
--xformers          # VRAM optimization
--opt-sdp-attention # PyTorch 2.0

--api               # Enable API
--no-half-vae       # Avoid black images
--precision full    # Precision issues

1. Change VAE
2. Use --no-half-vae
3. Adjust CFG to 7-8

Negative: bad hands, extra fingers
Use ADetailer
Use ControlNet OpenPose

Use ADetailer extension
Use face_yolov8n model
Add "detailed face" to prompt

Lower resolution
Reduce steps to 20-25
Use UniPC sampler
Enable xformers

Load Checkpoint  # Load model
CLIP Text Encode # Text encoding
KSampler         # Sampler
VAE Decode       # VAE decode
Save Image       # Save image

Checkpoint → CLIP → KSampler → VAE Decode → Save
                ↑
            Empty Latent