Add progress to vae decode tiled

comfy/sd.py

 import torch
 import contextlib
 import copy
+from tqdm.auto import tqdm
 
 import sd1_clip
 import sd2_clip
@@ -437,11 +438,16 @@ class VAE:
         self.device = device
 
     def decode_tiled_(self, samples, tile_x=64, tile_y=64, overlap = 16):
+        it_1 = -(samples.shape[2] // -(tile_y * 2 - overlap)) * -(samples.shape[3] // -(tile_x // 2 - overlap))
+        it_2 = -(samples.shape[2] // -(tile_y // 2 - overlap)) * -(samples.shape[3] // -(tile_x * 2 - overlap))
+        it_3 = -(samples.shape[2] // -(tile_y - overlap)) * -(samples.shape[3] // -(tile_x - overlap))
+        pbar = tqdm(total=samples.shape[0] * (it_1 + it_2 + it_3))
+
         decode_fn = lambda a: (self.first_stage_model.decode(1. / self.scale_factor * a.to(self.device)) + 1.0)
         output = torch.clamp((
-            (utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = 8) +
-            utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = 8) +
-             utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = 8))
+            (utils.tiled_scale(samples, decode_fn, tile_x // 2, tile_y * 2, overlap, upscale_amount = 8, pbar = pbar) +
+            utils.tiled_scale(samples, decode_fn, tile_x * 2, tile_y // 2, overlap, upscale_amount = 8, pbar = pbar) +
+             utils.tiled_scale(samples, decode_fn, tile_x, tile_y, overlap, upscale_amount = 8, pbar = pbar))
             / 3.0) / 2.0, min=0.0, max=1.0)
         return output
 

comfy/utils.py

@@ -63,7 +63,7 @@ def common_upscale(samples, width, height, upscale_method, crop):
         return torch.nn.functional.interpolate(s, size=(height, width), mode=upscale_method)
 
 @torch.inference_mode()
-def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_amount = 4, out_channels = 3):
+def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_amount = 4, out_channels = 3, pbar = None):
     output = torch.empty((samples.shape[0], out_channels, round(samples.shape[2] * upscale_amount), round(samples.shape[3] * upscale_amount)), device="cpu")
     for b in range(samples.shape[0]):
         s = samples[b:b+1]
@@ -83,6 +83,8 @@ def tiled_scale(samples, function, tile_x=64, tile_y=64, overlap = 8, upscale_am
                         mask[:,:,:,mask.shape[3]- 1 - t: mask.shape[3]- t] *= ((1.0/feather) * (t + 1))
                 out[:,:,round(y*upscale_amount):round((y+tile_y)*upscale_amount),round(x*upscale_amount):round((x+tile_x)*upscale_amount)] += ps * mask
                 out_div[:,:,round(y*upscale_amount):round((y+tile_y)*upscale_amount),round(x*upscale_amount):round((x+tile_x)*upscale_amount)] += mask
+                if pbar is not None:
+                    pbar.update(1)
 
         output[b:b+1] = out/out_div
     return output