Mirrors
/
stable-diffusion-webui
mirror of https://github.com/AUTOMATIC1111/stable-diffusion-webui.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Use shared.sd_model.is_sdxl to determine base AYS sigmas

This commit is contained in:
Logan 2024-05-10 18:05:45 +10:00
parent 73d1caf8f2
commit d6b4444069
1 changed files with 6 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
modules/sd_schedulers.py
View File

@ -6,6 +6,8 @@ import k_diffusion
import numpy as np import numpy as np
from modules import shared
@dataclasses.dataclass @dataclasses.dataclass
class Scheduler: class Scheduler:
name: str name: str
@ -31,7 +33,7 @@ def sgm_uniform(n, sigma_min, sigma_max, inner_model, device):
sigs += [0.0] sigs += [0.0]
return torch.FloatTensor(sigs).to(device) return torch.FloatTensor(sigs).to(device)
def get_align_your_steps_sigmas(n, device, sigma_id): def get_align_your_steps_sigmas(n, sigma_min, sigma_max, device):
# https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html # https://research.nvidia.com/labs/toronto-ai/AlignYourSteps/howto.html
def loglinear_interp(t_steps, num_steps): def loglinear_interp(t_steps, num_steps):
""" """
@ -46,12 +48,10 @@ def get_align_your_steps_sigmas(n, device, sigma_id):
interped_ys = np.exp(new_ys)[::-1].copy() interped_ys = np.exp(new_ys)[::-1].copy()
return interped_ys return interped_ys
if sigma_id == "sdxl": if shared.sd_model.is_sdxl:
sigmas = [14.615, 6.315, 3.771, 2.181, 1.342, 0.862, 0.555, 0.380, 0.234, 0.113, 0.029] sigmas = [14.615, 6.315, 3.771, 2.181, 1.342, 0.862, 0.555, 0.380, 0.234, 0.113, 0.029]
elif sigma_id == "sd15":
sigmas = [14.615, 6.475, 3.861, 2.697, 1.886, 1.396, 0.963, 0.652, 0.399, 0.152, 0.029]
else: else:
print(f'Align Your Steps sigma identifier "{sigma_id}" not recognized, defaulting to SD 1.5.') # Default to SD 1.5 sigmas.
sigmas = [14.615, 6.475, 3.861, 2.697, 1.886, 1.396, 0.963, 0.652, 0.399, 0.152, 0.029] sigmas = [14.615, 6.475, 3.861, 2.697, 1.886, 1.396, 0.963, 0.652, 0.399, 0.152, 0.029]
if n != len(sigmas): if n != len(sigmas):
@ -68,8 +68,7 @@ schedulers = [
Scheduler('exponential', 'Exponential', k_diffusion.sampling.get_sigmas_exponential), Scheduler('exponential', 'Exponential', k_diffusion.sampling.get_sigmas_exponential),
Scheduler('polyexponential', 'Polyexponential', k_diffusion.sampling.get_sigmas_polyexponential, default_rho=1.0), Scheduler('polyexponential', 'Polyexponential', k_diffusion.sampling.get_sigmas_polyexponential, default_rho=1.0),
Scheduler('sgm_uniform', 'SGM Uniform', sgm_uniform, need_inner_model=True, aliases=["SGMUniform"]), Scheduler('sgm_uniform', 'SGM Uniform', sgm_uniform, need_inner_model=True, aliases=["SGMUniform"]),
Scheduler('align_your_steps_sdxl', 'Align Your Steps (SDXL)', lambda n, sigma_min, sigma_max, device: get_align_your_steps_sigmas(n, device, "sdxl")), Scheduler('align_your_steps', 'Align Your Steps', get_align_your_steps_sigmas),
Scheduler('align_your_steps_sd15', 'Align Your Steps (SD 1.5)', lambda n, sigma_min, sigma_max, device: get_align_your_steps_sigmas(n, device, "sd15")),
] ]
schedulers_map = {**{x.name: x for x in schedulers}, **{x.label: x for x in schedulers}} schedulers_map = {**{x.name: x for x in schedulers}, **{x.label: x for x in schedulers}}