Text-to-Image
Diffusers
PyTorch
StableDiffusionPipeline
stable-diffusion
diffusion-models-class
dreambooth-hackathon
wildcard
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("sooolee/rex-the-toy-dinosaur_dreambooth", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of rxty dinosaur reading a book in a cafe"
image = pipe(prompt).images[0]DreamBooth model for the rxty concept trained by sooolee on the sooolee/rexthetoy dataset.
This is a Stable Diffusion model fine-tuned on the rxty concept with DreamBooth. It can be used by modifying the instance_prompt: a photo of rxty dinosaur
This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!
Description
This is a Stable Diffusion model fine-tuned on dinosaur images for the wildcard theme. The model was trained with a learning rate of 1e-06 and 1000 train steps.
Some Output Examples
Inferences were made with a guidance scale between 8 - 11 and inference steps of 300 - 400.
In Various Places
In the Style of Various Artists
Doing Things
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('sooolee/rex-the-toy-dinosaur')
image = pipeline().images[0]
image
- Downloads last month
- 121