add some codes for robust

modules/processing.py

@@ -108,17 +108,18 @@ def txt2img_image_conditioning(sd_model, x, width, height):
     else:
         sd = sd_model.model.state_dict()
         diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
-        if diffusion_model_input.shape[1] == 9:
-            # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
-            image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
-            image_conditioning = images_tensor_to_samples(image_conditioning,
-                                                          approximation_indexes.get(opts.sd_vae_encode_method))
+        if diffusion_model_input is not None:
+            if diffusion_model_input.shape[1] == 9:
+                # The "masked-image" in this case will just be all 0.5 since the entire image is masked.
+                image_conditioning = torch.ones(x.shape[0], 3, height, width, device=x.device) * 0.5
+                image_conditioning = images_tensor_to_samples(image_conditioning,
+                                                              approximation_indexes.get(opts.sd_vae_encode_method))
 
-            # 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)
+                # 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 image_conditioning
 
         # Dummy zero conditioning if we're not using inpainting or unclip models.
         # Still takes up a bit of memory, but no encoder call.
@@ -378,8 +379,9 @@ class StableDiffusionProcessing:
 
         sd = self.sampler.model_wrap.inner_model.model.state_dict()
         diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
-        if diffusion_model_input.shape[1] == 9:
-            return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
+        if diffusion_model_input is not None:
+            if diffusion_model_input.shape[1] == 9:
+                return self.inpainting_image_conditioning(source_image, latent_image, image_mask=image_mask)
 
         # Dummy zero conditioning if we're not using inpainting or depth model.
         return latent_image.new_zeros(latent_image.shape[0], 5, 1, 1)

modules/sd_models_xl.py

@@ -36,8 +36,9 @@ def get_learned_conditioning(self: sgm.models.diffusion.DiffusionEngine, batch:
 def apply_model(self: sgm.models.diffusion.DiffusionEngine, x, t, cond):
     sd = self.model.state_dict()
     diffusion_model_input = sd.get('diffusion_model.input_blocks.0.0.weight', None)
-    if diffusion_model_input.shape[1] == 9:
-        x = torch.cat([x] + cond['c_concat'], dim=1)
+    if diffusion_model_input is not None:
+        if diffusion_model_input.shape[1] == 9:
+            x = torch.cat([x] + cond['c_concat'], dim=1)
 
     return self.model(x, t, cond)