import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("AItool/evil-protagonist", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Dreambooth fine-tuned models for Stable Diffusion using d🧨ffusers: evil-protagonist
Prompt suggestion: <evil-protagonist> man in Chinatown
This your the Stable Diffusion model fine-tuned the Evil-protagonist concept taught to Stable Diffusion with Dreambooth.
It can be used by modifying the instance_prompt: <evil-protagonist>**.
You can also train your own concepts and upload them to the library by using this notebook.
And you can run your new concept via diffusers: Colab Notebook for Inference, Spaces with the Public Concepts loade SD Dreambooth Concepts
Here are the images used for training this concept:
All imagery was created using (Playgroundai.com) Thanks to ArtGen discord channel ArtGen discord channel.
Flickr inspiration https://www.flickr.com/photos/187488733@N06/albums/72177720316475593/
- Downloads last month
- 4