models/DnD Darkest Fantasy (SD1, SDXL, Pony, Flux) - Flux

DnD Darkest Fantasy (SD1, SDXL, Pony, Flux) - Flux

7/14/2025

5:19:23 AM

Related Keywords & Tags

arsmachina,arsmjstyle,d&d-themed,dark fantasy,dnd,dnd darkest fantasy,fantasy,fantasy image generation,flux,flux.1 d,lora,midjourney,style

Close-up hyperdetailed portrait of death featuring a skull with faintly glowing blue eyes, wearing a torn black hooded robe with a silver scythe ornament, set against a dark background.

Realistic painting of a fragile teen female angel with flowing white hair, delicate white wings, wearing 1500s white plate armor, holding a brass longsword in a warm Rembrandt lighting style.

Detailed portrait of Harley Quinn with white face paint and red-black designs, dramatic chiaroscuro lighting hitting one side of her face, wearing dark armor with skull motifs and chains.

Close-up portrait of a dark female rogue with blue eyes holding an obsidian assassin dagger coated with shimmering green poison, illuminated with warm Rembrandt-style lighting.

Artistic portrait of a woman with gold accents and grey tones, revealing a regal and mysterious expression.

Recommended Prompts

ArsMJStyle, dnddarkestfantasy

Recommended Parameters

samplers

Euler

steps

Tips

Use trigger words 'ArsMJStyle' and 'dnddarkestfantasy' for best results.

Start strength at 1 and adjust; distortions may occur above 1.3.

SD 1.5 version works well in the 0.2 to 1.2 strength range.

Version Highlights

The model works great in the 0.4 - 1.2 strength range.

The model is a little bit too eager to add Elf Ears everywhere. This disapears at 0.8 and lower strength.

All images in the Showcase Gallery were created using this workflow and the Flux Q4 Dev model on a machine with 8GB VRAM. Almost all were requests from my DnD Party.

https://civitai.com/models/658639/super-simple-gguf-quantized-flux-lora-workflow

This model is an experimental LoRA inspired by a unique D&D-themed concept.

The "DnD Darkest Fantasy" style was crafted with input from my primary D&D party, each contributing 1-3 fantasy images. These images were used as reference material in Midjourney, where I blended them with my own "Personalized Style" to create a distinctive aesthetic. The training dataset was exclusively generated from various "random D&D-themed requests" they provided.

Тhe trigger words are ArsMJStyle, dnddarkestfantasy .

Start around strentgh 1 and adjust accordingly.

Distortions may occur at strengths above 1.3

Update:
Added SD 1.5 that works well in the 0.2 - 1.2 range

And a big THANK YOU! to you all for making it so popular and making this the 3rd place of the "Flux Training Contest".