resolve an error when floats are provided for resolution values

examples/community/composable_stable_diffusion.py

@@ -321,7 +321,12 @@ def check_inputs(self, prompt, height, width, callback_steps):
             )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if latents is None:
             if device.type == "mps":
                 # randn does not work reproducibly on mps

examples/community/gluegen.py

@@ -500,7 +500,12 @@ def check_inputs(
                 )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/instaflow_one_step.py

@@ -468,7 +468,12 @@ def check_inputs(
                 )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/ip_adapter_face_id.py

@@ -1039,7 +1039,12 @@ def check_inputs(
                 )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/latent_consistency_img2img.py

@@ -177,7 +177,12 @@ def prepare_latents(
         latents=None,
         generator=None,
     ):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
 
         if not isinstance(image, (torch.Tensor, PIL.Image.Image, list)):
             raise ValueError(

examples/community/latent_consistency_interpolate.py

@@ -472,7 +472,12 @@ def run_safety_checker(self, image, device, dtype):
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/latent_consistency_txt2img.py

@@ -163,7 +163,12 @@ def run_safety_checker(self, image, device, dtype):
         return image, has_nsfw_concept
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if latents is None:
             latents = torch.randn(shape, dtype=dtype).to(device)
         else:

examples/community/lpw_stable_diffusion.py

@@ -726,7 +726,12 @@ def prepare_latents(
     ):
         if image is None:
             batch_size = batch_size * num_images_per_prompt
-            shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+            shape = (
+                batch_size,
+                num_channels_latents,
+                int(height) // self.vae_scale_factor,
+                int(width) // self.vae_scale_factor,
+            )
             if isinstance(generator, list) and len(generator) != batch_size:
                 raise ValueError(
                     f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/lpw_stable_diffusion_xl.py

@@ -1060,7 +1060,12 @@ def prepare_latents(
         batch_size *= num_images_per_prompt
 
         if image is None:
-            shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+            shape = (
+                batch_size,
+                num_channels_latents,
+                int(height) // self.vae_scale_factor,
+                int(width) // self.vae_scale_factor,
+            )
             if isinstance(generator, list) and len(generator) != batch_size:
                 raise ValueError(
                     f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -1140,7 +1145,12 @@ def prepare_latents(
             return latents
 
         else:
-            shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+            shape = (
+                batch_size,
+                num_channels_latents,
+                int(height) // self.vae_scale_factor,
+                int(width) // self.vae_scale_factor,
+            )
             if isinstance(generator, list) and len(generator) != batch_size:
                 raise ValueError(
                     f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -1214,7 +1224,7 @@ def prepare_mask_latents(
         # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
         # and half precision
         mask = torch.nn.functional.interpolate(
-            mask, size=(height // self.vae_scale_factor, width // self.vae_scale_factor)
+            mask, size=(int(height) // self.vae_scale_factor, int(width) // self.vae_scale_factor)
         )
         mask = mask.to(device=device, dtype=dtype)
 

examples/community/pipeline_demofusion_sdxl.py

@@ -477,7 +477,12 @@ def check_inputs(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/pipeline_sdxl_style_aligned.py

@@ -919,7 +919,12 @@ def prepare_latents(
         batch_size *= num_images_per_prompt
 
         if image is None:
-            shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+            shape = (
+                batch_size,
+                num_channels_latents,
+                int(height) // self.vae_scale_factor,
+                int(width) // self.vae_scale_factor,
+            )
             if isinstance(generator, list) and len(generator) != batch_size:
                 raise ValueError(
                     f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -999,7 +1004,12 @@ def prepare_latents(
             return latents
 
         else:
-            shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+            shape = (
+                batch_size,
+                num_channels_latents,
+                int(height) // self.vae_scale_factor,
+                int(width) // self.vae_scale_factor,
+            )
             if isinstance(generator, list) and len(generator) != batch_size:
                 raise ValueError(
                     f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -1050,7 +1060,7 @@ def prepare_mask_latents(
         # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
         # and half precision
         mask = torch.nn.functional.interpolate(
-            mask, size=(height // self.vae_scale_factor, width // self.vae_scale_factor)
+            mask, size=(int(height) // self.vae_scale_factor, int(width) // self.vae_scale_factor)
         )
         mask = mask.to(device=device, dtype=dtype)
 

examples/community/pipeline_stable_diffusion_pag.py

@@ -857,7 +857,12 @@ def check_inputs(
             )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/pipeline_stable_diffusion_xl_controlnet_adapter.py

@@ -751,7 +751,12 @@ def check_conditions(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/pipeline_stable_diffusion_xl_ipex.py

@@ -614,7 +614,12 @@ def check_inputs(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/pipeline_zero1to3.py

@@ -497,7 +497,12 @@ def check_inputs(self, image, height, width, callback_steps):
             )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/stable_diffusion_controlnet_inpaint.py

@@ -635,7 +635,12 @@ def check_inputs(
             )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"
@@ -656,7 +661,9 @@ def prepare_mask_latents(self, mask_image, batch_size, height, width, dtype, dev
         # resize the mask to latents shape as we concatenate the mask to the latents
         # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
         # and half precision
-        mask_image = F.interpolate(mask_image, size=(height // self.vae_scale_factor, width // self.vae_scale_factor))
+        mask_image = F.interpolate(
+            mask_image, size=(int(height) // self.vae_scale_factor, int(width) // self.vae_scale_factor)
+        )
         mask_image = mask_image.to(device=device, dtype=dtype)
 
         # duplicate mask for each generation per prompt, using mps friendly method

examples/community/stable_diffusion_controlnet_inpaint_img2img.py

@@ -648,7 +648,9 @@ def prepare_mask_latents(self, mask_image, batch_size, height, width, dtype, dev
         # resize the mask to latents shape as we concatenate the mask to the latents
         # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
         # and half precision
-        mask_image = F.interpolate(mask_image, size=(height // self.vae_scale_factor, width // self.vae_scale_factor))
+        mask_image = F.interpolate(
+            mask_image, size=(int(height) // self.vae_scale_factor, int(width) // self.vae_scale_factor)
+        )
         mask_image = mask_image.to(device=device, dtype=dtype)
 
         # duplicate mask for each generation per prompt, using mps friendly method

examples/community/stable_diffusion_ipex.py

@@ -533,7 +533,12 @@ def check_inputs(
                 )
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/stable_diffusion_reference.py

@@ -609,7 +609,12 @@ def prepare_latents(
         Returns:
             torch.Tensor: The prepared latent vectors.
         """
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/community/stable_diffusion_repaint.py

@@ -558,7 +558,7 @@ def prepare_mask_latents(
         # we do that before converting to dtype to avoid breaking in case we're using cpu_offload
         # and half precision
         mask = torch.nn.functional.interpolate(
-            mask, size=(height // self.vae_scale_factor, width // self.vae_scale_factor)
+            mask, size=(int(height) // self.vae_scale_factor, int(width) // self.vae_scale_factor)
         )
         mask = mask.to(device=device, dtype=dtype)
 

examples/research_projects/controlnetxs/pipeline_controlnet_xs.py

@@ -547,7 +547,12 @@ def prepare_image(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/research_projects/controlnetxs/pipeline_controlnet_xs_sd_xl.py

@@ -577,7 +577,12 @@ def prepare_image(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/research_projects/promptdiffusion/pipeline_prompt_diffusion.py

@@ -789,7 +789,12 @@ def prepare_image(
 
     # Copied from diffusers.pipelines.stable_diffusion.pipeline_stable_diffusion.StableDiffusionPipeline.prepare_latents
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"

examples/research_projects/rdm/pipeline_rdm.py

@@ -123,7 +123,12 @@ def _encode_image(self, retrieved_images, batch_size):
         return image_embeddings
 
     def prepare_latents(self, batch_size, num_channels_latents, height, width, dtype, device, generator, latents=None):
-        shape = (batch_size, num_channels_latents, height // self.vae_scale_factor, width // self.vae_scale_factor)
+        shape = (
+            batch_size,
+            num_channels_latents,
+            int(height) // self.vae_scale_factor,
+            int(width) // self.vae_scale_factor,
+        )
         if isinstance(generator, list) and len(generator) != batch_size:
             raise ValueError(
                 f"You have passed a list of generators of length {len(generator)}, but requested an effective batch"