stylize according to diffusers requirement

Author: Luciennnnnnn

src/diffusers/pipelines/flux/pipeline_flux.py

@@ -386,8 +386,10 @@ def check_inputs(
         callback_on_step_end_tensor_inputs=None,
         max_sequence_length=None,
     ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs

src/diffusers/pipelines/flux/pipeline_flux_controlnet.py

@@ -410,8 +410,10 @@ def check_inputs(
         callback_on_step_end_tensor_inputs=None,
         max_sequence_length=None,
     ):
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
@@ -504,7 +506,7 @@ def prepare_latents(
         shape = (batch_size, num_channels_latents, height, width)
 
         if latents is not None:
-            latent_image_ids = self._prepare_latent_image_ids(batch_size, height // 2, width // 2, device, dtype)
+            latent_image_ids = self._prepare_latent_image_ids(batch_size, height, width, device, dtype)
             return latents.to(device=device, dtype=dtype), latent_image_ids
 
         if isinstance(generator, list) and len(generator) != batch_size:

src/diffusers/pipelines/flux/pipeline_flux_controlnet_image_to_image.py

@@ -453,8 +453,10 @@ def check_inputs(
         if strength < 0 or strength > 1:
             raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
 
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs

src/diffusers/pipelines/flux/pipeline_flux_controlnet_inpainting.py

@@ -467,8 +467,10 @@ def check_inputs(
         if strength < 0 or strength > 1:
             raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
 
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs
@@ -996,7 +998,9 @@ def __call__(
         # 6. Prepare timesteps
 
         sigmas = np.linspace(1.0, 1 / num_inference_steps, num_inference_steps)
-        image_seq_len = (int(global_height) // self.vae_scale_factor // 2) * (int(global_width) // self.vae_scale_factor // 2)
+        image_seq_len = (int(global_height) // self.vae_scale_factor // 2) * (
+            int(global_width) // self.vae_scale_factor // 2
+        )
         mu = calculate_shift(
             image_seq_len,
             self.scheduler.config.base_image_seq_len,

src/diffusers/pipelines/flux/pipeline_flux_img2img.py

@@ -437,8 +437,10 @@ def check_inputs(
         if strength < 0 or strength > 1:
             raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
 
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs

src/diffusers/pipelines/flux/pipeline_flux_inpaint.py

@@ -445,8 +445,10 @@ def check_inputs(
         if strength < 0 or strength > 1:
             raise ValueError(f"The value of strength should in [0.0, 1.0] but is {strength}")
 
-        if height % 8 != 0 or width % 8 != 0:
-            raise ValueError(f"`height` and `width` have to be divisible by 8 but are {height} and {width}.")
+        if height % self.vae_scale_factor != 0 or width % self.vae_scale_factor != 0:
+            raise ValueError(
+                f"`height` and `width` have to be divisible by {self.vae_scale_factor} but are {height} and {width}."
+            )
 
         if callback_on_step_end_tensor_inputs is not None and not all(
             k in self._callback_tensor_inputs for k in callback_on_step_end_tensor_inputs