metadata
license: other
license_name: bespoke-lora-trained-license
license_link: >-
https://multimodal.art/civitai-licenses?allowNoCredit=True&allowCommercialUse=Image&allowDerivatives=True&allowDifferentLicense=True
tags:
- text-to-image
- stable-diffusion
- lora
- diffusers
- template:sd-lora
- migrated
- style
base_model: black-forest-labs/FLUX.1-dev
instance_prompt: dndstyle
widget:
- text: dndstyle illustration of two characters, castle in the background
output:
url: 27073838.jpeg
- text: >-
dndstyle illustration of a female knight, standing with a sword in one
hand and a helmet under her arm and a fire breathing dragon in the
background
output:
url: 27073771.jpeg
- text: dndstyle illustration of a castle in the mountains
output:
url: 27074290.jpeg
- text: >-
dndstyle illustration of a young female knight, standing with a sword on
one shoulder, helmet under her arm and a dead dragon in the background
output:
url: 27074050.jpeg
- text: dndstyle illustration of an elfin thief
output:
url: 27074115.jpeg
- text: dndstyle illustration of a fire breathing dragon, castle in the background
output:
url: 27074021.jpeg
- text: dndstyle illustration of a Goblin
output:
url: 27083250.jpeg
- text: dndstyle illustration of a Skeleton warrior
output:
url: 27083536.jpeg
- text: dndstyle illustration of a beholder
output:
url: 27083714.jpeg
- text: dndstyle illustration of a Aarakocra
output:
url: 27084020.jpeg
- text: dndstyle illustration of a Barghest
output:
url: 27084273.jpeg
DnD Style - Flux
Model description
dndstyle is the trigger word. DnD style lora trained on a vast dataset of DnD illustrations. For prompts see my sample image.
I use SwarmUI for 95% of my image generations and encourage you to try it out! Here's the link to the GitHub repo and also checkout this install video from Kleebz Tech AI to get you started!
Trigger words
You should use dndstyle
to trigger the image generation.
Download model
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.
Use it with the 🧨 diffusers library
from diffusers import AutoPipelineForText2Image
import torch
device = "cuda" if torch.cuda.is_available() else "cpu"
pipeline = AutoPipelineForText2Image.from_pretrained('black-forest-labs/FLUX.1-dev', torch_dtype=torch.bfloat16).to(device)
pipeline.load_lora_weights('SouthbayJay/dnd-style-flux', weight_name='dnd_style_flux.safetensors')
image = pipeline('dndstyle illustration of a Barghest').images[0]
For more details, including weighting, merging and fusing LoRAs, check the documentation on loading LoRAs in diffusers