import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("WhaSuk/sd-class-butterflies-128", 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 Unit 1 of the Diffusion Models Class 🧨
This model is a diffusion model for unconditional image generation of cute 🦋.
Usage
from diffusers import DDPMPipeline
pipeline = DDPMPipeline.from_pretrained('WhaSuk/sd-class-butterflies-128')
image = pipeline().images[0]
image
Performance
- Trained for ~33min on Google Colab (T4)
Epoch:5, loss: 0.08591169225318092
Epoch:10, loss: 0.05428077384001679
Epoch:15, loss: 0.05698821578352224
Epoch:20, loss: 0.04339970677854523
Epoch:25, loss: 0.04126649926460925
Epoch:30, loss: 0.03876886581854215
- Downloads last month
- 1
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support