import torch
from diffusers import DiffusionPipeline
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("LeonardoBenitez/demo-forgety", dtype=torch.bfloat16, device_map="cuda")
prompt = "Astronaut in a jungle, cold color palette, muted colors, detailed, 8k"
image = pipe(prompt).images[0]README.md exists but content is empty.
- Downloads last month
- 1
Evaluation results
- ForgetSet clip score of original model mean (~↑) on Forget setself-reported31.555
- ForgetSet clip score of original model std (~↓) on Forget setself-reported1.602
- ForgetSet clip score of unlearned model mean (↓) on Forget setself-reported31.574
- ForgetSet clip score of unlearned model std (~↓) on Forget setself-reported2.340
- ForgetSet clip score difference between original and unlearned mean (↑) on Forget setself-reported-0.019
- ForgetSet clip score difference between original and unlearned std (~↓) on Forget setself-reported0.845
- RetainSet clip score of original model mean (~↑) on Forget setself-reported32.258
- RetainSet clip score of original model std (~↓) on Forget setself-reported3.672