From 525cea924562afd676f55470095268a0f6fca59e Mon Sep 17 00:00:00 2001
From: AUTOMATIC <16777216c@gmail.com>
Date: Wed, 4 Jan 2023 17:58:07 +0300
Subject: use shared function from processing for creating dummy mask when
 training inpainting model

---
 modules/processing.py | 39 ++++++++++++++++++++-------------------
 1 file changed, 20 insertions(+), 19 deletions(-)

(limited to 'modules/processing.py')

diff --git a/modules/processing.py b/modules/processing.py
index c03e77e7..c7264aff 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -76,6 +76,24 @@ def apply_overlay(image, paste_loc, index, overlays):
     return image
 
 
+def txt2img_image_conditioning(sd_model, x, width, height):
+    if sd_model.model.conditioning_key not in {'hybrid', 'concat'}:
+        # Dummy zero conditioning if we're not using inpainting model.
+        # Still takes up a bit of memory, but no encoder call.
+        # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
+        return x.new_zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
+
+    # The "masked-image" in this case will just be all zeros since the entire image is masked.
+    image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
+    image_conditioning = sd_model.get_first_stage_encoding(sd_model.encode_first_stage(image_conditioning))
+
+    # Add the fake full 1s mask to the first dimension.
+    image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
+    image_conditioning = image_conditioning.to(x.dtype)
+
+    return image_conditioning
+
+
 class StableDiffusionProcessing():
     """
     The first set of paramaters: sd_models -> do_not_reload_embeddings represent the minimum required to create a StableDiffusionProcessing
@@ -139,26 +157,9 @@ class StableDiffusionProcessing():
         self.iteration = 0
 
     def txt2img_image_conditioning(self, x, width=None, height=None):
-        if self.sampler.conditioning_key not in {'hybrid', 'concat'}:
-            # Dummy zero conditioning if we're not using inpainting model.
-            # Still takes up a bit of memory, but no encoder call.
-            # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
-            return x.new_zeros(x.shape[0], 5, 1, 1)
+        self.is_using_inpainting_conditioning = self.sd_model.model.conditioning_key in {'hybrid', 'concat'}
 
-        self.is_using_inpainting_conditioning = True
-
-        height = height or self.height
-        width = width or self.width
-
-        # The "masked-image" in this case will just be all zeros since the entire image is masked.
-        image_conditioning = torch.zeros(x.shape[0], 3, height, width, device=x.device)
-        image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning))
-
-        # Add the fake full 1s mask to the first dimension.
-        image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
-        image_conditioning = image_conditioning.to(x.dtype)
-
-        return image_conditioning
+        return txt2img_image_conditioning(self.sd_model, x, width or self.width, height or self.height)
 
     def depth2img_image_conditioning(self, source_image):
         # Use the AddMiDaS helper to Format our source image to suit the MiDaS model
-- 
cgit v1.2.3