Instructions to use ShadoWxShinigamI/midjourney-graffiti with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use ShadoWxShinigamI/midjourney-graffiti with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("ShadoWxShinigamI/midjourney-graffiti", 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
model by ShadoWxShinigamI
It can be used by adding in the style of mdjrny-grfft to the end of your prompt. (Token is mdjrny-grfft, but since the weight is too strong (over trained text encoder), using the full sentence can help in better style transfer (YMMV)).
NO PROMPT ENGINEERING REQUIRED.
Trained On TheLastBen Repo Fast Method :- (https://colab.research.google.com/github/TheLastBen/fast-stable-diffusion/blob/main/fast-DreamBooth.ipynb).
And you can run your new concept via diffusers: Colab Notebook for Inference, Spaces with the Public Concepts loaded
Examples :-
Human :-
Creatures :-
Animals/Birds
Butterfly ( I know it's neither an animal/bird )

Objects - Semi Reliable ( Have to Cherry Pick. Usually 1 in 3 will be good )
Try adding weights if your prompt doesn't work. All the best!!
- Downloads last month
- 151














