import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("etweedy/tessa", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Tessa on Stable Diffusion v1.5 via Dreambooth
This is a Stable Diffusion (v1.5) model fine-tuned on the concept of my dog, Tessa, usiung the Dreambooth method: https://dreambooth.github.io/ To use the model, try modifying the basic prompt: "a photo of <tessa> dog".
The model was fine-tuned for 1200 steps with a learning rate of 2e-6, using 15 images of Tessa and 500 class regularization images. The class images were generated in advance by Stable Diffusion v1.5 using the prompt "Photo of a dog".
Here are the images of Tessa used for training this concept:
- Downloads last month
- 3