pip install -U diffusers transformers accelerate
import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("plankton-rpl/plankton", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]Model Card for Model ID
This is my first test to train a diffusion model from scratch. It is composed of a simple UNet that denoises the noisy images. This is trained in a subset of the WHOI-PLankton dataset (only a part of the 2006 images). It was trained in a single Nvidia T4, ~6 minutes per epoch.
- Downloads last month
- -
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support
# Gated model: Login with a HF token with gated access permission hf auth login