Hack to load custom depth map

hack.diff

diff --git a/modules/processing.py b/modules/processing.py
index 0417ffc..c2bde57 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -154,15 +154,17 @@ class StableDiffusionProcessing():
         return image_conditioning
 
     def depth2img_image_conditioning(self, source_image):
-        # Use the AddMiDaS helper to Format our source image to suit the MiDaS model
-        transformer = AddMiDaS(model_type="dpt_hybrid")
-        transformed = transformer({"jpg": rearrange(source_image[0], "c h w -> h w c")})
-        midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
-        midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
+        depth_img = Image.open("/home/jay/Pictures/AI/Turrent Room/depth.png")
+        depth_img = depth_img.convert("L")
+        depth_img = np.expand_dims(depth_img, axis=0)
+        depth_img = np.expand_dims(depth_img, axis=0).repeat(self.batch_size, axis=0)
+        depth_img = torch.from_numpy(depth_img)
+        depth_img = 2. * depth_img - 1.
+        depth_img = depth_img.to(shared.device)
 
         conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image))
         conditioning = torch.nn.functional.interpolate(
-            self.sd_model.depth_model(midas_in),
+            depth_img,
             size=conditioning_image.shape[2:],
             mode="bicubic",
             align_corners=False,

+1, would be amazing to have this in the the a1111 interface to select a synthetic depth map, instead of computing one using MiDaS