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
- Draw Things
- DiffusionBee
v2-diffusers
#9
by keturn - opened
This is diffusers-format conversion for DnD_Classes_and_Species with EMA-only weights at fp16 size.
The previous diffusers pickles (for the previous model) have been removed in this PR.
I don't know what the convention is for all that, if π€ expects you to make different branches or repos for those various types.
Converted using
convert_original_stable_diffusion_to_diffusers.py \
--checkpoint_path DnD_Classes_and_Species.ckpt
--extract_ema \
--image_size 512 \
--prediction_type epsilon
then converted to safetensors by loading that with
pipe = StableDiffusionPipeline.from_pretrained("./DnD-CnS", torch_dtype=torch.float16)
pipe.save_pretrained("DnD-CnS-safe", True)
keturn changed pull request status to open
0xJustin changed pull request status to merged
thanks!