OPENGIT/stable-diffusion-webui
1
0
Fork 0
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git synced 2024-12-29 02:45:05 +08:00
Code Issues Packages Projects Releases Wiki Activity

patch k_diffusion to_d and strip device from schedulers

Browse Source
This commit is contained in:
drhead 2024-06-08 18:55:07 -04:00 committed by GitHub
parent 428975e1d3
commit 39a6d5655f
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 15 additions and 9 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

24
modules/sd_schedulers.py
View File

@ -4,6 +4,12 @@ import torch
import k_diffusion
def to_d(x, sigma, denoised):
"""Converts a denoiser output to a Karras ODE derivative."""
return (x - denoised) / sigma
k_diffusion.sampling.to_d = to_d
import numpy as np
from modules import shared
@ -19,11 +25,11 @@ class Scheduler:
aliases: list = None
def uniform(n, sigma_min, sigma_max, inner_model, device):
def uniform(n, sigma_min, sigma_max, inner_model):
return inner_model.get_sigmas(n)
def sgm_uniform(n, sigma_min, sigma_max, inner_model, device):
def sgm_uniform(n, sigma_min, sigma_max, inner_model):
start = inner_model.sigma_to_t(torch.tensor(sigma_max))
end = inner_model.sigma_to_t(torch.tensor(sigma_min))
sigs = [
@ -31,9 +37,9 @@ def sgm_uniform(n, sigma_min, sigma_max, inner_model, device):
for ts in torch.linspace(start, end, n + 1)[:-1]
]
sigs += [0.0]
return torch.FloatTensor(sigs).to(device)
return torch.FloatTensor(sigs)
def get_align_your_steps_sigmas(n, sigma_min, sigma_max, device='cpu'):
def get_align_your_steps_sigmas(n, sigma_min, sigma_max):
# https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html
def loglinear_interp(t_steps, num_steps):
"""
@ -59,12 +65,12 @@ def get_align_your_steps_sigmas(n, sigma_min, sigma_max, device='cpu'):
else:
sigmas.append(0.0)
return torch.FloatTensor(sigmas).to(device)
return torch.FloatTensor(sigmas)
def kl_optimal(n, sigma_min, sigma_max, device):
alpha_min = torch.arctan(torch.tensor(sigma_min, device=device))
alpha_max = torch.arctan(torch.tensor(sigma_max, device=device))
step_indices = torch.arange(n + 1, device=device)
def kl_optimal(n, sigma_min, sigma_max):
alpha_min = torch.arctan(torch.tensor(sigma_min))
alpha_max = torch.arctan(torch.tensor(sigma_max))
step_indices = torch.arange(n + 1)
sigmas = torch.tan(step_indices / n * alpha_min + (1.0 - step_indices / n) * alpha_max)
return sigmas