import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("AItool/diva-protagonist", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]diva-protagonist on Stable Diffusion via Dreambooth
This your the Stable Diffusion model fine-tuned the diva-protagonist concept taught to Stable Diffusion with Dreambooth.
It can be used by modifying the instance_prompt: **<diva-protagonist> woman
Prompt suggestion: a <diva-protagonist> on a black and white movie
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 loaded
Here are the images used for training this concept:
Here are two outputs:
- Downloads last month
- 1