trygvebw

# This is an abbreviated demonstration of how to perform this technique. The code
# is a simplified version of that in my own custom codebase, and can't be plugged
# into other ways of using Stable Diffusion (e.g. Diffusers or A1111) without changes.

# In essence, the observation that the CFG formula:
#
#     output_noise = uncond_noise + (cond_noise - uncond_noise) * scale
#
# looks a lot like the formula for the unsharp mask, a common way to sharpen or add local contrast to images:
#

trygvebw

import torch
import numpy as np
import k_diffusion as K

from PIL import Image
from torch import autocast
from einops import rearrange, repeat

def pil_img_to_torch(pil_img, half=False):
    image = np.array(pil_img).astype(np.float32) / 255.0

trygvebw

def normalize_latent(x, max_val, quantile_val):
    x = x.detach().clone()
    for i in range(x.shape[0]):
        if x[[i], :].std() > 1.0:
            x[[i], :] = x[[i], :] / x[[i], :].std()
        s = torch.quantile(torch.abs(x[[i], :]), quantile_val)
        s = torch.maximum(s, torch.ones_like(s) * max_val)
        x[[i], :] = x[[i], :] / (s / max_val)
    return x