Made dummy latents smaller. Minor code cleanups

modules/processing.py

@@ -557,7 +557,8 @@ class StableDiffusionProcessingTxt2Img(StableDiffusionProcessing):
         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)
+            # Pretty sure we can just make this a 1x1 image since its not going to be used besides its batch size.
+            image_conditioning = torch.zeros(x.shape[0], 5, 1, 1, dtype=x.dtype, device=x.device)
 
         return image_conditioning
 
@@ -759,8 +760,8 @@ class StableDiffusionProcessingImg2Img(StableDiffusionProcessing):
             self.image_conditioning = self.image_conditioning.to(shared.device).type(self.sd_model.dtype)
         else:
             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, 
+                self.init_latent.shape[0], 5, 1, 1,
+                dtype=self.init_latent.dtype,
                 device=self.init_latent.device
             )
 

modules/sd_samplers.py

@@ -138,7 +138,7 @@ class VanillaStableDiffusionSampler:
         if self.stop_at is not None and self.step > self.stop_at:
             raise InterruptedException
 
-        # Have to unwrap the inpainting conditioning here to perform pre-preocessing
+        # Have to unwrap the inpainting conditioning here to perform pre-processing
         image_conditioning = None
         if isinstance(cond, dict):
             image_conditioning = cond["c_concat"][0]
@@ -146,7 +146,7 @@ class VanillaStableDiffusionSampler:
             unconditional_conditioning = unconditional_conditioning["c_crossattn"][0]
 
         conds_list, tensor = prompt_parser.reconstruct_multicond_batch(cond, self.step)
-        unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)            
+        unconditional_conditioning = prompt_parser.reconstruct_cond_batch(unconditional_conditioning, self.step)
 
         assert all([len(conds) == 1 for conds in conds_list]), 'composition via AND is not supported for DDIM/PLMS samplers'
         cond = tensor
@@ -165,6 +165,8 @@ class VanillaStableDiffusionSampler:
             img_orig = self.sampler.model.q_sample(self.init_latent, ts)
             x_dec = img_orig * self.mask + self.nmask * x_dec
 
+        # Wrap the image conditioning back up since the DDIM code can accept the dict directly.
+        # Note that they need to be lists because it just concatenates them later.
         if image_conditioning is not None:
             cond = {"c_concat": [image_conditioning], "c_crossattn": [cond]}
             unconditional_conditioning = {"c_concat": [image_conditioning], "c_crossattn": [unconditional_conditioning]}