Fix HunyuanVideo 1.5 I2V by preprocessing image at pixel resolution i… (#13440)

Fix HunyuanVideo 1.5 I2V by preprocessing image at pixel resolution instead of latent resolution

docs/source/en/quicktour.md

@@ -101,9 +101,9 @@ export_to_video(video, "output.mp4", fps=16)
 
 ## LoRA
 
-Adapters insert a small number of trainable parameters to the original base model. Only the inserted parameters are fine-tuned while the rest of the model weights remain frozen. This makes it fast and cheap to fine-tune a model on a new style. Among adapters, [LoRA's](./tutorials/using_peft_for_inference) are the most popular.
+Adapters insert a small number of trainable parameters to the original base model. Only the inserted parameters are fine-tuned while the rest of the model weights remain frozen. This makes it fast and cheap to fine-tune a model on a new style. Among adapters, [LoRAs](./tutorials/using_peft_for_inference) are the most popular.
 
-Add a LoRA to a pipeline with the [`~loaders.QwenImageLoraLoaderMixin.load_lora_weights`] method. Some LoRA's require a special word to trigger it, such as `Realism`, in the example below. Check a LoRA's model card to see if it requires a trigger word.
+Add a LoRA to a pipeline with the [`~loaders.QwenImageLoraLoaderMixin.load_lora_weights`] method. Some LoRAs require a special word to trigger them, such as `Realism`, in the example below. Check a LoRA's model card to see if it requires a trigger word.
 
 ```py
 import torch

src/diffusers/pipelines/hunyuan_video1_5/pipeline_hunyuan_video1_5_image2video.py

@@ -611,7 +611,7 @@ class HunyuanVideo15ImageToVideoPipeline(DiffusionPipeline):
             tuple: (cond_latents_concat, mask_concat) - both are zero tensors for t2v
         """
 
-        batch, channels, frames, height, width = latents.shape
+        batch, channels, frames, latent_height, latent_width = latents.shape
 
         image_latents = self._get_image_latents(
             vae=self.vae,
@@ -626,7 +626,7 @@ class HunyuanVideo15ImageToVideoPipeline(DiffusionPipeline):
         latent_condition[:, :, 1:, :, :] = 0
         latent_condition = latent_condition.to(device=device, dtype=dtype)
 
-        latent_mask = torch.zeros(batch, 1, frames, height, width, dtype=dtype, device=device)
+        latent_mask = torch.zeros(batch, 1, frames, latent_height, latent_width, dtype=dtype, device=device)
         latent_mask[:, :, 0, :, :] = 1.0
 
         return latent_condition, latent_mask