Merge remote-tracking branch 'origin/master'

modules/processing.py

@@ -79,7 +79,7 @@ class StableDiffusionProcessing:
         self.paste_to = None
         self.color_corrections = None
         self.denoising_strength: float = 0
-
+        self.sampler_noise_scheduler_override = None
         self.ddim_discretize = opts.ddim_discretize
         self.s_churn = opts.s_churn
         self.s_tmin = opts.s_tmin
@@ -130,7 +130,7 @@ class Processed:
         self.s_tmin = p.s_tmin
         self.s_tmax = p.s_tmax
         self.s_noise = p.s_noise
-        
+        self.sampler_noise_scheduler_override = p.sampler_noise_scheduler_override
         self.prompt = self.prompt if type(self.prompt) != list else self.prompt[0]
         self.negative_prompt = self.negative_prompt if type(self.negative_prompt) != list else self.negative_prompt[0]
         self.seed = int(self.seed if type(self.seed) != list else self.seed[0])

modules/sd_samplers.py

@@ -290,6 +290,9 @@ class KDiffusionSampler:
     def sample_img2img(self, p, x, noise, conditioning, unconditional_conditioning, steps=None):
         steps, t_enc = setup_img2img_steps(p, steps)
 
+        if p.sampler_noise_scheduler_override:
+          sigmas = p.sampler_noise_scheduler_override(steps)
+        else:
           sigmas = self.model_wrap.get_sigmas(steps)
 
         noise = noise * sigmas[steps - t_enc - 1]
@@ -306,6 +309,9 @@ class KDiffusionSampler:
     def sample(self, p, x, conditioning, unconditional_conditioning, steps=None):
         steps = steps or p.steps
 
+        if p.sampler_noise_scheduler_override:
+          sigmas = p.sampler_noise_scheduler_override(steps)
+        else:
           sigmas = self.model_wrap.get_sigmas(steps)
         x = x * sigmas[0]
 

modules/swinir_model.py

@@ -5,6 +5,7 @@ import numpy as np
 import torch
 from PIL import Image
 from basicsr.utils.download_util import load_file_from_url
+from tqdm import tqdm
 
 from modules import modelloader
 from modules.paths import models_path
@@ -122,6 +123,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
     E = torch.zeros(b, c, h * sf, w * sf, dtype=torch.half, device=device).type_as(img)
     W = torch.zeros_like(E, dtype=torch.half, device=device)
 
+    with tqdm(total=len(h_idx_list) * len(w_idx_list), desc="SwinIR tiles") as pbar:
         for h_idx in h_idx_list:
             for w_idx in w_idx_list:
                 in_patch = img[..., h_idx: h_idx + tile, w_idx: w_idx + tile]
@@ -134,6 +136,7 @@ def inference(img, model, tile, tile_overlap, window_size, scale):
                 W[
                 ..., h_idx * sf: (h_idx + tile) * sf, w_idx * sf: (w_idx + tile) * sf
                 ].add_(out_patch_mask)
+                pbar.update(1)
     output = E.div_(W)
 
     return output