metadata

license: cc-by-nc-4.0
language:
  - en
base_model:
  - stabilityai/stable-diffusion-xl-base-1.0
tags:
  - SDXL
  - text-to-image
  - ComfyUI
  - Automatic1111
  - Diffuser
widget:
  - text: >-
      realistic, photorealistic, very aesthetic, best quality, absurdres,
      masterpiece, best quality, amazing quality, newest, scenery, depth of
      field, high-resolution, high definition, visually intense anaglyphic
      experience, hallucinations, editorial photography, journalistic style,
      candid, volumetric, candid, bow, fake animal ears, pleated skirt,
      thighhighs, 2girls, multiple girls, (colorful:1.2), rainbow, light
      particles, from above, volumetric lighting, ((adult girls:1.2)), _trippy_,
      realistic, photorealistic, very aesthetic, best quality, absurdres,
      masterpiece, best quality, amazing quality, newest, scenery, depth of
      field
    parameters:
      negative_prompt: >-
        bad hands, extra digits, (multiple views:1.1), (bad:1.05), fewer, extra,
        missing, worst quality, jpeg artifacts, bad quality, watermark,
        unfinished, displeasing, sepia, sketch, flat color, signature, artistic
        error, username, scan, (blurry, lowres, worst quality, (low
        quality:1.1), ugly, (bad anatomy:1.05), artist name, (patreon
        username:1.2)
    output:
      url: stand_on_the_ice.png

MIDNIGHT Illustrious Checkpoint

Overview

The MIDNIGHT Illustrious checkpoint is a versatile and photorealistic model built for producing high-quality, aesthetically intense outputs. Optimized for SDXL, this model is suitable for creating editorial, journalistic, and artistic images with incredible detail and depth. The focus is on realistic imagery with stunning visual intensity, blending realism and creativity.

Prompt Format

Positive

realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, amazing quality, newest, scenery, depth of field, high-resolution, high definition, visually intense anaglyphic experience, hallucinations, editorial photography, journalistic style, candid

Place your creative description in the middle:

Your Prompt Here

realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, amazing quality, newest, scenery, depth of field

Example Prompt

a vibrant cityscape at night, glowing neon signs, people walking in rain-soaked streets, cinematic lighting, reflections on wet pavement

realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, amazing quality, newest, scenery, depth of field

Negative

bad hands, extra digits, (multiple views:1.1), (bad:1.05), fewer, extra, missing, worst quality, jpeg artifacts, bad quality, watermark, unfinished, displeasing, sepia, sketch, flat color, signature, artistic error, username, scan, (blurry, lowres, worst quality, (low quality:1.1), ugly, (bad anatomy:1.05), artist name, (patreon username:1.2)

Settings

Sampling Methods:
- Euler A (Euler ancestral)
- DPM++ 2M Karras
- DPM++ 2M SDE Karras
- DPM++ 3M SDE Exponential
Sampling Steps: 25–45
CFG Scale: 7
Clip Skip: 1

Additional Notes

Outputs are best suited for ComfyUI, Automatic1111, and other Diffuser-based tools.
🔧 Usage with Hugging Face Inference API

You can use this model with the Hugging Face Inference API for generating images directly from code. Here's a sample Python script:

from huggingface_hub import InferenceClient

# Initialize the Inference Client
client = InferenceClient(
    provider="hf-inference",
    api_key="hf_xxxxxxxxxxxxxxxxxxxxxxxx"  # Replace with your Hugging Face API key
)

# Generate an image
image = client.text_to_image(
    "realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, best quality, amazing quality, newest, scenery, depth of field, high-resolution, high definition, visually intense anaglyphic experience, hallucinations, editorial photography, journalistic style, candid, volumetric, candid, bow, fake animal ears, pleated skirt, thighhighs, 2girls, multiple girls, (colorful:1.2), rainbow, light particles, from above, volumetric lighting, ((adult girls:1.2)), _trippy_, realistic, photorealistic, very aesthetic, best quality, absurdres, masterpiece, best quality, amazing quality, newest, scenery, depth of field",
    model="MidnightRunner/MDNT_Illus/blob/main/MIDNIGHT_illustrious_BakedVAE20V18.safetensors"
)

# Save or display the image
image.save("generated_image.png")
image.show()

## License

2025 © MidnightRunner & Midnight1111  
**Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0)**