Instructions to use 0xJustin/Dungeons-and-Diffusion with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use 0xJustin/Dungeons-and-Diffusion with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("0xJustin/Dungeons-and-Diffusion", dtype=torch.bfloat16, device_map="cuda") prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Draw Things
- DiffusionBee
Any thought on adding some races and classes from other DnD materials?
Been fiddling around with this model for a while and and love it so far, and I want to make a character from a D&D campaign I'm currently in with it, a Kilnkin Pugilist, both the race and class are from the Ultimate Adventurers Handbook but Kilnkin are very...odd, to say the least. They're more or less just funky little golems and they're unlike anything that you've trained your model with that i could tell from the dataset cards
anyways. Could be neat to see.
The issue is training data- I think 30 examples of a race is good enough to train, so lesser known races can be tough. You might be able to use warforged as a base and prompt around to try and get a guy like that. I've been able to prompt it to make wooden warforged or warforged made of lava. Might be worth a shot :)