A Flux.1 Krea version of this model is available on Mage with free and unlimited generations for October. For more Halloween models, visit: darkinfinity.art/halloween.

I post models on multiple sites, including exclusive ones on specific platforms. Follow me on X (Twitter) or Instagram for new model releases, bounties, and more.

Unlock the Secrets of the Unseen

Step into the shadows of arcane knowledge with "The Forbidden Book", a LoRA designed to bring the cryptic pages of ancient, forbidden tomes to life. Inspired by imagined occult manuscripts like the Compendium Maleficarum, Codex Diaboli, and the legendary Necronomicon, this model conjures a style steeped in mystery and darkness.

The Forbidden Book creates images that appear as if they’ve been ripped from the fragile pages of an eldritch grimoire—worn, tattered, and alive with dark energy. Summon imagery covered in intricate runes, ominous symbols, and unsettling sketches that echo the hidden truths and sinister wisdom of the occult. From bizarre creatures that dwell between worlds to eerie diagrams and mystical glyphs, this LoRA weaves tales of the unknown onto your canvas.

This LoRA is made as part of the KI Welten Discord Group Collaboration. For the other Great Halloween-themed Flux LoRAs, follow the link to the KiWelten Halloween Collection.

Usage

To use the most recent version of the LoRA, use the following settings:

• Trigger word: frbddnbk

• Other tokens that work well: An ancient manuscript, On a stained piece of parchment, A discolored and frayed page, A torn and faded manuscript page

• Lora Strength: Full Strength (1.0) is recommended, but play with ranges from 0.8 to 1.2

For differences in previous versions, see the version notes below.

Version Notes

Version 4.0

I consider Version 4.0 of the Forbidden Book a different, but not necessarily better, version of the LoRA. Some will like it more, while others will want to stay with v1. This version was retrained with fewer and more closely cropped images, resulting in a LoRA that is much different than v1.0. Though the overall style is the same, v2.0 has more illustrations that aren't quite as otherworldly, and the model focuses more on the images than the script. As a result of the revisions, the model follows prompts better and will generate readable text, but it feels more like an occult tome than a truly unholy book from the abyss.

Version 1.0

Note: Version 1.0 uses trigger word "ncrnmcn"

The first version of The Forbidden Book was trained on a large number of captionless images. The overall style was captured well, and it transformed a good number of prompts into torn and better-forgotten pages. Its best to start describing the medium, then the primary illustrations, and then how the runes and symbols will flow throughout the page.