mirror of
https://github.com/lllyasviel/stable-diffusion-webui-forge.git
synced 2025-12-28 05:35:00 +00:00
114 lines
4.5 KiB
Python
114 lines
4.5 KiB
Python
import torch
|
|
import numpy as np
|
|
|
|
from PIL import Image
|
|
|
|
|
|
def bislerp(samples, width, height):
|
|
def slerp(b1, b2, r):
|
|
'''slerps batches b1, b2 according to ratio r, batches should be flat e.g. NxC'''
|
|
|
|
c = b1.shape[-1]
|
|
|
|
# norms
|
|
b1_norms = torch.norm(b1, dim=-1, keepdim=True)
|
|
b2_norms = torch.norm(b2, dim=-1, keepdim=True)
|
|
|
|
# normalize
|
|
b1_normalized = b1 / b1_norms
|
|
b2_normalized = b2 / b2_norms
|
|
|
|
# zero when norms are zero
|
|
b1_normalized[b1_norms.expand(-1, c) == 0.0] = 0.0
|
|
b2_normalized[b2_norms.expand(-1, c) == 0.0] = 0.0
|
|
|
|
# slerp
|
|
dot = (b1_normalized * b2_normalized).sum(1)
|
|
omega = torch.acos(dot)
|
|
so = torch.sin(omega)
|
|
|
|
# technically not mathematically correct, but more pleasing?
|
|
res = (torch.sin((1.0 - r.squeeze(1)) * omega) / so).unsqueeze(1) * b1_normalized + (torch.sin(r.squeeze(1) * omega) / so).unsqueeze(1) * b2_normalized
|
|
res *= (b1_norms * (1.0 - r) + b2_norms * r).expand(-1, c)
|
|
|
|
# edge cases for same or polar opposites
|
|
res[dot > 1 - 1e-5] = b1[dot > 1 - 1e-5]
|
|
res[dot < 1e-5 - 1] = (b1 * (1.0 - r) + b2 * r)[dot < 1e-5 - 1]
|
|
return res
|
|
|
|
def generate_bilinear_data(length_old, length_new, device):
|
|
coords_1 = torch.arange(length_old, dtype=torch.float32, device=device).reshape((1, 1, 1, -1))
|
|
coords_1 = torch.nn.functional.interpolate(coords_1, size=(1, length_new), mode="bilinear")
|
|
ratios = coords_1 - coords_1.floor()
|
|
coords_1 = coords_1.to(torch.int64)
|
|
|
|
coords_2 = torch.arange(length_old, dtype=torch.float32, device=device).reshape((1, 1, 1, -1)) + 1
|
|
coords_2[:, :, :, -1] -= 1
|
|
coords_2 = torch.nn.functional.interpolate(coords_2, size=(1, length_new), mode="bilinear")
|
|
coords_2 = coords_2.to(torch.int64)
|
|
return ratios, coords_1, coords_2
|
|
|
|
orig_dtype = samples.dtype
|
|
samples = samples.float()
|
|
n, c, h, w = samples.shape
|
|
h_new, w_new = (height, width)
|
|
|
|
# linear w
|
|
ratios, coords_1, coords_2 = generate_bilinear_data(w, w_new, samples.device)
|
|
coords_1 = coords_1.expand((n, c, h, -1))
|
|
coords_2 = coords_2.expand((n, c, h, -1))
|
|
ratios = ratios.expand((n, 1, h, -1))
|
|
|
|
pass_1 = samples.gather(-1, coords_1).movedim(1, -1).reshape((-1, c))
|
|
pass_2 = samples.gather(-1, coords_2).movedim(1, -1).reshape((-1, c))
|
|
ratios = ratios.movedim(1, -1).reshape((-1, 1))
|
|
|
|
result = slerp(pass_1, pass_2, ratios)
|
|
result = result.reshape(n, h, w_new, c).movedim(-1, 1)
|
|
|
|
# linear h
|
|
ratios, coords_1, coords_2 = generate_bilinear_data(h, h_new, samples.device)
|
|
coords_1 = coords_1.reshape((1, 1, -1, 1)).expand((n, c, -1, w_new))
|
|
coords_2 = coords_2.reshape((1, 1, -1, 1)).expand((n, c, -1, w_new))
|
|
ratios = ratios.reshape((1, 1, -1, 1)).expand((n, 1, -1, w_new))
|
|
|
|
pass_1 = result.gather(-2, coords_1).movedim(1, -1).reshape((-1, c))
|
|
pass_2 = result.gather(-2, coords_2).movedim(1, -1).reshape((-1, c))
|
|
ratios = ratios.movedim(1, -1).reshape((-1, 1))
|
|
|
|
result = slerp(pass_1, pass_2, ratios)
|
|
result = result.reshape(n, h_new, w_new, c).movedim(-1, 1)
|
|
return result.to(orig_dtype)
|
|
|
|
|
|
def lanczos(samples, width, height):
|
|
images = [Image.fromarray(np.clip(255. * image.movedim(0, -1).cpu().numpy(), 0, 255).astype(np.uint8)) for image in samples]
|
|
images = [image.resize((width, height), resample=Image.Resampling.LANCZOS) for image in images]
|
|
images = [torch.from_numpy(np.array(image).astype(np.float32) / 255.0).movedim(-1, 0) for image in images]
|
|
result = torch.stack(images)
|
|
return result.to(samples.device, samples.dtype)
|
|
|
|
|
|
def adaptive_resize(samples, width, height, upscale_method, crop):
|
|
if crop == "center":
|
|
old_width = samples.shape[3]
|
|
old_height = samples.shape[2]
|
|
old_aspect = old_width / old_height
|
|
new_aspect = width / height
|
|
x = 0
|
|
y = 0
|
|
if old_aspect > new_aspect:
|
|
x = round((old_width - old_width * (new_aspect / old_aspect)) / 2)
|
|
elif old_aspect < new_aspect:
|
|
y = round((old_height - old_height * (old_aspect / new_aspect)) / 2)
|
|
s = samples[:, :, y:old_height - y, x:old_width - x]
|
|
else:
|
|
s = samples
|
|
|
|
if upscale_method == "bislerp":
|
|
return bislerp(s, width, height)
|
|
elif upscale_method == "lanczos":
|
|
return lanczos(s, width, height)
|
|
else:
|
|
return torch.nn.functional.interpolate(s, size=(height, width), mode=upscale_method)
|