Text-to-Image
Diffusers
TensorBoard
PyTorch
StableDiffusionPipeline
stable-diffusion
diffusion-models-class
dreambooth-hackathon
food
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("morgan/torta", dtype=torch.bfloat16, device_map="cuda")
prompt = "a photo of a field of tortas"
image = pipe(prompt).images[0]DreamBooth model for the torta concept trained by morgan on the morgan/tortas dataset.
This is a Stable Diffusion model fine-tuned on the torta concept with DreamBooth. It can be used by modifying the instance_prompt: a photo of a torta sandwich
See the ongoing experiments here in this Weights & Biases training journal
This model was created as part of the DreamBooth Hackathon 🔥. Visit the organisation page for instructions on how to take part!
Note that commit 8f89857b2b2a6f75c443eac298f022483ef23a3f uses the concept name zztortazz instead of torta, to see if this more unique concept name works better (spoiler, it doesn't)
Description
This is a Stable Diffusion model fine-tuned on images of tortas.
Usage
from diffusers import StableDiffusionPipeline
pipeline = StableDiffusionPipeline.from_pretrained('morgan/torta')
image = pipeline().images[0]
image
- Downloads last month
- 3