Don't compute latent mask if were not using it. Also added support for fixed highres_fix generation.

modules/processing.py

@@ -541,12 +541,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             self.truncate_y = int(self.firstphase_height - firstphase_height_truncated) // opt_f
 
 
-    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
-        self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)
-
-        if not self.enable_hr:
-            x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-            
+    def create_dummy_mask(self, x):
+        if self.sampler.conditioning_key in {'hybrid', 'concat'}:
             # 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, self.height, self.width, device=x.device)
             image_conditioning = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(image_conditioning)) 
@@ -555,11 +551,23 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
             image_conditioning = torch.nn.functional.pad(image_conditioning, (0, 0, 0, 0, 1, 0), value=1.0)
             image_conditioning = image_conditioning.to(x.dtype)
 
-            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=image_conditioning)
+        else:
+            # Dummy zero conditioning if we're not using inpainting model.
+            # Still takes up a bit of memory, but no encoder call.
+            image_conditioning = torch.zeros(x.shape[0], 5, x.shape[-2], x.shape[-1], dtype=x.dtype, device=x.device)
+
+        return image_conditioning
+
+    def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
+        self.sampler = sd_samplers.create_sampler_with_index(sd_samplers.samplers, self.sampler_index, self.sd_model)
+
+        if not self.enable_hr:
+            x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
+            samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x))
             return samples
 
         x = create_random_tensors([opt_C, self.firstphase_height // opt_f, self.firstphase_width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)
-        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning)
+        samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.create_dummy_mask(x))
 
         samples = samples[:, :, self.truncate_y//2:samples.shape[2]-self.truncate_y//2, self.truncate_x//2:samples.shape[3]-self.truncate_x//2]
 
@@ -596,7 +604,7 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         x = None
         devices.torch_gc()
 
-        samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps)
+        samples = self.sampler.sample_img2img(self, samples, noise, conditioning, unconditional_conditioning, steps=self.steps, image_conditioning=self.create_dummy_mask(samples))
 
         return samples
 
@@ -723,26 +731,36 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             elif self.inpainting_fill == 3:
                 self.init_latent = self.init_latent * self.mask
 
-        if self.image_mask is not None:
-            conditioning_mask = np.array(self.image_mask.convert("L"))
-            conditioning_mask = conditioning_mask.astype(np.float32) / 255.0
-            conditioning_mask = torch.from_numpy(conditioning_mask[None, None])
+        conditioning_key = self.sampler.conditioning_key
 
-            # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
-            conditioning_mask = torch.round(conditioning_mask)
+        if conditioning_key in {'hybrid', 'concat'}:
+            if self.image_mask is not None:
+                conditioning_mask = np.array(self.image_mask.convert("L"))
+                conditioning_mask = conditioning_mask.astype(np.float32) / 255.0
+                conditioning_mask = torch.from_numpy(conditioning_mask[None, None])
+
+                # Inpainting model uses a discretized mask as input, so we round to either 1.0 or 0.0
+                conditioning_mask = torch.round(conditioning_mask)
+            else:
+                conditioning_mask = torch.ones(1, 1, *image.shape[-2:])
+
+            # Create another latent image, this time with a masked version of the original input.
+            conditioning_mask = conditioning_mask.to(image.device)
+            conditioning_image = image * (1.0 - conditioning_mask)
+            conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
+
+            # Create the concatenated conditioning tensor to be fed to `c_concat`
+            conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=self.init_latent.shape[-2:])
+            conditioning_mask = conditioning_mask.expand(conditioning_image.shape[0], -1, -1, -1)
+            self.image_conditioning = torch.cat([conditioning_mask, conditioning_image], dim=1)
+            self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype)
         else:
-            conditioning_mask = torch.ones(1, 1, *image.shape[-2:])
+            self.image_conditioning = torch.zeros(
+                self.init_latent.shape[0], 5, self.init_latent.shape[-2], self.init_latent.shape[-1], 
+                dtype=self.init_latent.dtype, 
+                device=self.init_latent.device
+            )
 
-        # Create another latent image, this time with a masked version of the original input.
-        conditioning_mask = conditioning_mask.to(image.device)
-        conditioning_image = image * (1.0 - conditioning_mask)
-        conditioning_image = self.sd_model.get_first_stage_encoding(self.sd_model.encode_first_stage(conditioning_image))
-
-        # Create the concatenated conditioning tensor to be fed to `c_concat`
-        conditioning_mask = torch.nn.functional.interpolate(conditioning_mask, size=self.init_latent.shape[-2:])
-        conditioning_mask = conditioning_mask.expand(conditioning_image.shape[0], -1, -1, -1)
-        self.image_conditioning = torch.cat([conditioning_mask, conditioning_image], dim=1)
-        self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype)
 
     def sample(self, conditioning, unconditional_conditioning, seeds, subseeds, subseed_strength):
         x = create_random_tensors([opt_C, self.height // opt_f, self.width // opt_f], seeds=seeds, subseeds=subseeds, subseed_strength=self.subseed_strength, seed_resize_from_h=self.seed_resize_from_h, seed_resize_from_w=self.seed_resize_from_w, p=self)

modules/sd_samplers.py

@@ -117,6 +117,8 @@ class VanillaStableDiffusionSampler:
         self.config = None
         self.last_latent = None
 
+        self.conditioning_key = sd_model.model.conditioning_key
+
     def number_of_needed_noises(self, p):
         return 0
 
@@ -328,6 +330,8 @@ class KDiffusionSampler:
         self.config = None
         self.last_latent = None
 
+        self.conditioning_key = sd_model.model.conditioning_key
+
     def callback_state(self, d):
         step = d['i']
         latent = d["denoised"]