Merge branch 'tiled-progress' of https://github.com/pythongosssss/ComfyUI

comfy/sd.py

@@ -514,11 +514,14 @@ class VAE:
         self.device = device
 
     def decode_tiled_(self, samples, tile_x=64, tile_y=64, overlap = 16):
+        steps = samples.shape[0] * utils.get_tiled_scale_steps(samples.shape[3], samples.shape[2], tile_x, tile_y, overlap)
+        pbar = utils.ProgressBar(steps)
+
         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
 
@@ -562,9 +565,13 @@ class VAE:
         model_management.unload_model()
         self.first_stage_model = self.first_stage_model.to(self.device)
         pixel_samples = pixel_samples.movedim(-1,1).to(self.device)
-        samples = utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x, tile_y, overlap, upscale_amount = (1/8), out_channels=4)
-        samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/8), out_channels=4)
-        samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/8), out_channels=4)
+
+        steps = utils.get_tiled_scale_steps(pixel_samples.shape[3], pixel_samples.shape[2], tile_x, tile_y, overlap)
+        pbar = utils.ProgressBar(steps)
+
+        samples = utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x, tile_y, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
+        samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x * 2, tile_y // 2, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
+        samples += utils.tiled_scale(pixel_samples, lambda a: self.first_stage_model.encode(2. * a - 1.).sample() * self.scale_factor, tile_x // 2, tile_y * 2, overlap, upscale_amount = (1/8), out_channels=4, pbar=pbar)
         samples /= 3.0
         self.first_stage_model = self.first_stage_model.cpu()
         samples = samples.cpu()

comfy/utils.py

@@ -62,8 +62,14 @@ def common_upscale(samples, width, height, upscale_method, crop):
             s = samples
         return torch.nn.functional.interpolate(s, size=(height, width), mode=upscale_method)
 
+def get_tiled_scale_steps(width, height, tile_x, tile_y, overlap):
+    it_1 = -(height // -(tile_y * 2 - overlap)) * -(width // -(tile_x // 2 - overlap))
+    it_2 = -(height // -(tile_y // 2 - overlap)) * -(width // -(tile_x * 2 - overlap))
+    it_3 = -(height // -(tile_y - overlap)) * -(width // -(tile_x - overlap))
+    return it_1 + it_2 + it_3
+
 @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 +89,8 @@ 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

comfy_extras/nodes_upscale_model.py

@@ -37,7 +37,12 @@ class ImageUpscaleWithModel:
         device = model_management.get_torch_device()
         upscale_model.to(device)
         in_img = image.movedim(-1,-3).to(device)
-        s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=128 + 64, tile_y=128 + 64, overlap = 8, upscale_amount=upscale_model.scale)
+
+        tile = 128 + 64
+        overlap = 8
+        steps = -(in_img.shape[2] // -(tile - overlap)) * -(in_img.shape[3] // -(tile - overlap))
+        pbar = comfy.utils.ProgressBar(steps)
+        s = comfy.utils.tiled_scale(in_img, lambda a: upscale_model(a), tile_x=tile, tile_y=tile, overlap=overlap, upscale_amount=upscale_model.scale, pbar=pbar)
         upscale_model.cpu()
         s = torch.clamp(s.movedim(-3,-1), min=0, max=1.0)
         return (s,)