1 files changed, 12 insertions, 6 deletions
diff --git a/modules/processing.py b/modules/processing.py
index cb41288a..5072fc40 100644
--- a/modules/processing.py
+++ b/modules/processing.py
@@ -13,10 +13,11 @@ from skimage import exposure
 from typing import Any, Dict, List, Optional
 
 import modules.sd_hijack
-from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks, sd_vae_approx
+from modules import devices, prompt_parser, masking, sd_samplers, lowvram, generation_parameters_copypaste, script_callbacks, extra_networks, sd_vae_approx, scripts
 from modules.sd_hijack import model_hijack
 from modules.shared import opts, cmd_opts, state
 import modules.shared as shared
+import modules.paths as paths
 import modules.face_restoration
 import modules.images as images
 import modules.styles
@@ -172,7 +173,7 @@ class StableDiffusionProcessing:
         midas_in = torch.from_numpy(transformed["midas_in"][None, ...]).to(device=shared.device)
         midas_in = repeat(midas_in, "1 ... -> n ...", n=self.batch_size)
 
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image.to(devices.dtype_unet) if devices.unet_needs_upcast else source_image))
+        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(source_image.to(devices.dtype_vae) if devices.unet_needs_upcast else source_image))
         conditioning_image = conditioning_image.float() if devices.unet_needs_upcast else conditioning_image
         conditioning = torch.nn.functional.interpolate(
             self.sd_model.depth_model(midas_in),
@@ -217,7 +218,7 @@ class StableDiffusionProcessing:
         )
 
         # Encode the new masked image using first stage of network.
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image.to(devices.dtype_unet) if devices.unet_needs_upcast else conditioning_image))
+        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image.to(devices.dtype_vae) if devices.unet_needs_upcast else conditioning_image))
 
         # Create the concatenated conditioning tensor to be fed to `c_concat`
         conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=latent_image.shape[-2:])
@@ -417,7 +418,7 @@ def create_random_tensors(shape, seeds, subseeds=None, subseed_strength=0.0, see
 
 def decode_first_stage(model, x):
     with devices.autocast(disable=x.dtype == devices.dtype_vae):
-        x = model.decode_first_stage(x)
+        x = model.decode_first_stage(x.to(devices.dtype_vae) if devices.unet_needs_upcast else x)
 
     return x
 
@@ -584,7 +585,7 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
             if not p.disable_extra_networks:
                 extra_networks.activate(p, extra_network_data)
 
-        with open(os.path.join(shared.script_path, "params.txt"), "w", encoding="utf8") as file:
+        with open(os.path.join(paths.data_path, "params.txt"), "w", encoding="utf8") as file:
             processed = Processed(p, [], p.seed, "")
             file.write(processed.infotext(p, 0))
 
@@ -658,6 +659,11 @@ def process_images_inner(p: StableDiffusionProcessing) -> Processed:
 
                 image = Image.fromarray(x_sample)
 
+                if p.scripts is not None:
+                    pp = scripts.PostprocessImageArgs(image)
+                    p.scripts.postprocess_image(p, pp)
+                    image = pp.image
+
                 if p.color_corrections is not None and i < len(p.color_corrections):
                     if opts.save and not p.do_not_save_samples and opts.save_images_before_color_correction:
                         image_without_cc = apply_overlay(image, p.paste_to, i, p.overlay_images)
@@ -1001,7 +1007,7 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
 
         image = torch.from_numpy(batch_images)
         image = 2. * image - 1.
-        image = image.to(device=shared.device, dtype=devices.dtype_unet if devices.unet_needs_upcast else None)
+        image = image.to(device=shared.device, dtype=devices.dtype_vae if devices.unet_needs_upcast else None)
 
         self.init_latent = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image))