Join the CyberDelia AI Lab Discord!
Hang out with other AI creators, share ideas and resources, get early access to experimental tools and checkpoints, and help shape the growing community. 🚀
Semi-Realistic V1.0 bridges the painterly elegance of Illustrious with the crisp, lifelike look of CyberRealistic.
Think: clean realism with a soft artistic touch - strong anatomy, polished skin and fabric detail, cinematic light, and smooth tag understanding for Illustrious-style prompts.
If you liked CyberIllustrious and CyberIllustrious Catalyst, this version goes further: clearer tag comprehension, steadier faces, better skin/detail handling, and more consistent semi-realistic renders - especially when paired with my Danbooru Prompt Crafter GPT.
Why Early Access?
This model is available early to supporters and is . Early access helps me iterate faster with your feedback and push updates based on real-world use.
→ If you want the newest builds, experiments, and prompt tools, and grab Semi-Realistic V1.0 there.
What it’s great at
Semi-realistic portraits & fashion/editorial (soft glam → polished photoreal)
Character work that keeps a natural look while honoring Illustrious tag style
Cinematic lighting & moody color without over-baking effects
Cleaner hands, eyes, and hair with fewer artifacts at low CFG
Recommended Settings
Sampler: DPM++ SDE Karras / DPM++ 2M Karras / Euler a
Steps: 30–40
CFG: 4–5
Resolution: 896×1152 or 832×1216 (portrait-leaning works best)
VAE: Baked-in
Optional (face refiners):
ADetailer
face_yolov9c.ptIf you only want the main face refined, set “Mask only the top k largest” to 1.
Danbooru Prompt Crafter (GPT)
I’ve updated the Danbooru Prompt Crafter with a larger Danbooru tag list for more accurate, detailed prompts.
It’s built to write, clean, and optimize prompts for models that use Danbooru-style tags.
What it does
Converts descriptions to Danbooru tags: paste a natural sentence, messy tag list, or even an image → get a clean, copy-ready prompt.
Cleans up messy prompts: reorders tags, removes duplicates, and replaces vague terms with precise, valid Danbooru tags.
Multiple modes:
Strict Mode → accurate, clean Danbooru tagging.
Creative Mode (default) → adds aesthetic polish for more visually appealing results.
Output types:
Realism (default) → for photorealistic images.
Anime/Art → for stylized or illustrated outputs.
Tag validation & correction: fixes misspelled/invalid tags automatically.
Flexible formatting: choose commas, underscores, or spaces.
Understands images: upload an image; it analyzes character, pose, fashion, background, and lighting to generate a Danbooru-style prompt.
Compared to CyberIllustrious & Catalyst
Stronger semi-realistic bias (less experimental, more consistent)
Improved Illustrious tag comprehension (cleaner outputs from complex tag strings)
Better skin, hair, and eye detail
Smoother lighting roll-off and fewer harsh highlights
Notes & Etiquette
This model can generate mature content. Use responsibly and follow platform rules.
No explicit deepfakes of real people. Don’t be that person. 🙃
Support & Early Access
If this model helps your work, consider supporting the lab.
Patreon gets you early builds, exclusive tools (like the Prompt Crafter GPT integrations), and behind-the-scenes experiments. Your support directly funds training and testing.