Raise warning and round down if Wan num_frames is not 4k + 1 (#11167)

* update

* raise warning and round to nearest multiple of scale factor

src/diffusers/pipelines/wan/pipeline_wan.py

@@ -458,6 +458,13 @@ class WanPipeline(DiffusionPipeline, WanLoraLoaderMixin):
             callback_on_step_end_tensor_inputs,
         )
 
+        if num_frames % self.vae_scale_factor_temporal != 1:
+            logger.warning(
+                f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
+            )
+            num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
+        num_frames = max(num_frames, 1)
+
         self._guidance_scale = guidance_scale
         self._attention_kwargs = attention_kwargs
         self._current_timestep = None

src/diffusers/pipelines/wan/pipeline_wan_i2v.py

@@ -559,6 +559,13 @@ class WanImageToVideoPipeline(DiffusionPipeline, WanLoraLoaderMixin):
             callback_on_step_end_tensor_inputs,
         )
 
+        if num_frames % self.vae_scale_factor_temporal != 1:
+            logger.warning(
+                f"`num_frames - 1` has to be divisible by {self.vae_scale_factor_temporal}. Rounding to the nearest number."
+            )
+            num_frames = num_frames // self.vae_scale_factor_temporal * self.vae_scale_factor_temporal + 1
+        num_frames = max(num_frames, 1)
+
         self._guidance_scale = guidance_scale
         self._attention_kwargs = attention_kwargs
         self._current_timestep = None