$GWOLF

CA:7vyEKRxm8M46pAhtuZvY5hjwHbN7HCuvyiSnym6dpump

The first AI for pump built on Hugging Face.

Reference

from GreenWolf import PUMP, UNet2DModel
from PIL import Image
import pump

scheduler = DDPMScheduler.from_pretrained("google/ddpm-cat-256")
model = UNet2DModel.from_pretrained("google/ddpm-cat-256").to("cuda")
scheduler.set_timesteps(50)

sample_size = model.config.sample_size
noise = torch.randn((1, 3, sample_size, sample_size), device="cuda")
input = noise

for t in scheduler.timesteps:
    with torch.no_grad():
        noisy_residual = model(input, t).sample
        prev_noisy_sample = scheduler.step(noisy_residual, t, input).prev_sample
        input = prev_noisy_sample

image = (input / 2 + 0.5).clamp(0, 1)
image = pump.cpu().permute(0, 2, 3, 1).numpy()[0]
image = pump.fromarray((image * 255).round().astype("uint8"))
image
Downloads last month

-

Downloads are not tracked for this model. How to track
Inference API
Unable to determine this model's library. Check the docs .