Sign In

Ink & Lore

43

238

19

20

Verified:

SafeTensor

Type

LoRA

Stats

28

1

12

Reviews

Published

Oct 6, 2025

Base Model

Flux.1 D

Training

Epochs: 11

Usage Tips

Strength: 1

Trigger Words

distrnmyth

Hash

AutoV2
212FE0D06A

The FLUX.1 [dev] Model is licensed by Black Forest Labs. Inc. under the FLUX.1 [dev] Non-Commercial License. Copyright Black Forest Labs. Inc.

IN NO EVENT SHALL BLACK FOREST LABS, INC. BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH USE OF THIS MODEL.

I post models on multiple sites, including exclusive models. For new model releases, bounties, and more, follow me on: X (Twitter) or Instagram. Also, check out LoRA Lore for information on how to train your own models. More info & links: www.darkinfinity.art

Ink & Lore is a series of stylistic LoRAs designed to evoke the visual spirit of old-world myth, memory, and legend through hybridized folk art traditions drawn from ancient cultures.

Scrollbound Lore

Scrollbound Lore complements Forgotten Tales (the first LoRA in the Ink & Lore series). This LoRA generates illustrations in a storybook-meets-woodblock style, strongly leaning toward Asian myths and legends. It is trained on a mix of traditional asian art styles from Japan, China, and Vietnam, and more modern depictions of various mythological and legendary characters, spirits, and creatures. Subjects are depicted with clean outlines, flat expressive shading, and balanced, muted color palettes reminiscent of the traditional Japanese and East Asian woodblock prints, and backgrounds often feature natural or symbolic elements — moons, mountains, temples, water, or spirits — creating the feel of mythic scenes frozen in time.

Usage

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

  • Trigger word: trained with distrnmyth, but it isn't always necessary.

  • Other tokens that work well: animals, spirits, yokai, and other elements of magic and folklore.

  • Lora Strength: A strength between 0.8 and 1.2 is recommended. 1.0 seems perfect for most generations.

  • The LoRA was trained on Flux.1 Krea, but works on Flux.1 Dev as well.

For differences in previous versions, see the version notes to the right.

Showcase Credits - Scrollbound Lore

Thank you to the following AI artists and creators who participated in the Create my showcase bounty and helped make images to show what this model can do. If you like using my models, consider letting me pay you a buzz to build the showcase post for my next model. For more details, see Dark Infinity's Pre-release Models.

These are the artists responsible for the showcase images:

Showcase Credits - Forgotten Tales

Thank you to the following AI artists and creators who participated in the Create my showcase bounty and helped make images to show what this model can do. If you like using my models, consider letting me pay you a buzz to build the showcase post for my next model. For more details, see Dark Infinity's Pre-release Models.

These are the artists responsible for the showcase images: