diff options
Diffstat (limited to 'modules/sd_samplers.py')
| -rw-r--r-- | modules/sd_samplers.py | 43 |
1 files changed, 28 insertions, 15 deletions
diff --git a/modules/sd_samplers.py b/modules/sd_samplers.py index 3670b57d..783992d2 100644 --- a/modules/sd_samplers.py +++ b/modules/sd_samplers.py @@ -1,5 +1,6 @@ from collections import namedtuple
import numpy as np
+from math import floor
import torch
import tqdm
from PIL import Image
@@ -11,6 +12,7 @@ from modules import prompt_parser, devices, processing, images from modules.shared import opts, cmd_opts, state
import modules.shared as shared
+from modules.script_callbacks import CFGDenoiserParams, cfg_denoiser_callback
SamplerData = namedtuple('SamplerData', ['name', 'constructor', 'aliases', 'options'])
@@ -22,11 +24,15 @@ samplers_k_diffusion = [ ('Heun', 'sample_heun', ['k_heun'], {}),
('DPM2', 'sample_dpm_2', ['k_dpm_2'], {}),
('DPM2 a', 'sample_dpm_2_ancestral', ['k_dpm_2_a'], {}),
+ ('DPM++ 2S a', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a'], {}),
+ ('DPM++ 2M', 'sample_dpmpp_2m', ['k_dpmpp_2m'], {}),
('DPM fast', 'sample_dpm_fast', ['k_dpm_fast'], {}),
('DPM adaptive', 'sample_dpm_adaptive', ['k_dpm_ad'], {}),
('LMS Karras', 'sample_lms', ['k_lms_ka'], {'scheduler': 'karras'}),
('DPM2 Karras', 'sample_dpm_2', ['k_dpm_2_ka'], {'scheduler': 'karras'}),
('DPM2 a Karras', 'sample_dpm_2_ancestral', ['k_dpm_2_a_ka'], {'scheduler': 'karras'}),
+ ('DPM++ 2S a Karras', 'sample_dpmpp_2s_ancestral', ['k_dpmpp_2s_a_ka'], {'scheduler': 'karras'}),
+ ('DPM++ 2M Karras', 'sample_dpmpp_2m', ['k_dpmpp_2m_ka'], {'scheduler': 'karras'}),
]
samplers_data_k_diffusion = [
@@ -91,8 +97,8 @@ def single_sample_to_image(sample): return Image.fromarray(x_sample)
-def sample_to_image(samples):
- return single_sample_to_image(samples[0])
+def sample_to_image(samples, index=0):
+ return single_sample_to_image(samples[index])
def samples_to_image_grid(samples):
@@ -205,17 +211,22 @@ class VanillaStableDiffusionSampler: self.mask = p.mask if hasattr(p, 'mask') else None
self.nmask = p.nmask if hasattr(p, 'nmask') else None
+
+ def adjust_steps_if_invalid(self, p, num_steps):
+ if (self.config.name == 'DDIM' and p.ddim_discretize == 'uniform') or (self.config.name == 'PLMS'):
+ valid_step = 999 / (1000 // num_steps)
+ if valid_step == floor(valid_step):
+ return int(valid_step) + 1
+
+ return num_steps
+
+
def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None, image_conditioning=None):
steps, t_enc = setup_img2img_steps(p, steps)
-
+ steps = self.adjust_steps_if_invalid(p, steps)
self.initialize(p)
- # existing code fails with certain step counts, like 9
- try:
- self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
- except Exception:
- self.sampler.make_schedule(ddim_num_steps=steps+1, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
-
+ self.sampler.make_schedule(ddim_num_steps=steps, ddim_eta=self.eta, ddim_discretize=p.ddim_discretize, verbose=False)
x1 = self.sampler.stochastic_encode(x, torch.tensor([t_enc] * int(x.shape[0])).to(shared.device), noise=noise)
self.init_latent = x
@@ -239,18 +250,14 @@ class VanillaStableDiffusionSampler: self.last_latent = x
self.step = 0
- steps = steps or p.steps
+ steps = self.adjust_steps_if_invalid(p, steps or p.steps)
# Wrap the conditioning models with additional image conditioning for inpainting model
if image_conditioning is not None:
conditioning = {"c_concat": [image_conditioning], "c_crossattn": [conditioning]}
unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}
- # existing code fails with certain step counts, like 9
- try:
- samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
- except Exception:
- samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps+1, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
+ samples_ddim = self.launch_sampling(steps, lambda: self.sampler.sample(S=steps, conditioning=conditioning, batch_size=int(x.shape[0]), shape=x[0].shape, verbose=False, unconditional_guidance_scale=p.cfg_scale, unconditional_conditioning=unconditional_conditioning, x_T=x, eta=self.eta)[0])
return samples_ddim
@@ -278,6 +285,12 @@ class CFGDenoiser(torch.nn.Module): image_cond_in = torch.cat([torch.stack([image_cond[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [image_cond])
sigma_in = torch.cat([torch.stack([sigma[i] for _ in range(n)]) for i, n in enumerate(repeats)] + [sigma])
+ denoiser_params = CFGDenoiserParams(x_in, image_cond_in, sigma_in, state.sampling_step, state.sampling_steps)
+ cfg_denoiser_callback(denoiser_params)
+ x_in = denoiser_params.x
+ image_cond_in = denoiser_params.image_cond
+ sigma_in = denoiser_params.sigma
+
if tensor.shape[1] == uncond.shape[1]:
cond_in = torch.cat([tensor, uncond])
|