import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("sd-dreambooth-library/crisimsestelle", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Contain Real Ingredients on Stable Diffusion 2 via Dreambooth
model by estelleflores
This is a Stable Diffusion 2 model fine-tuned to the CRIsimsEstelle concept taught to Stable Diffusion with Dreambooth.
It can be used by modifying the instance_prompt: 3d render in <cri-sims> style or just using the initializer '<cri-sims> style' somewhere in your prompt will work.
Images used for training this concept come from the project Contain Real Ingredients, an art practice inside the game The Sims 4 by artist Estelle Flores:
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
- Downloads last month
- 3