README.md: fix demo code.

README.md

@@ -136,14 +136,20 @@ pipe.to("cuda")
 pipe_upsample.to("cuda")
 pipe.vae.enable_tiling()
 
+def round_to_nearest_resolution_acceptable_by_vae(height, width):
+    height = height - (height % pipe.vae_spatial_compression_ratio)
+    width = width - (width % pipe.vae_spatial_compression_ratio)
+    return height, width
+
 prompt = "The video depicts a winding mountain road covered in snow, with a single vehicle traveling along it. The road is flanked by steep, rocky cliffs and sparse vegetation. The landscape is characterized by rugged terrain and a river visible in the distance. The scene captures the solitude and beauty of a winter drive through a mountainous region."
 negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-expected_height, expected_width = 704, 512
+expected_height, expected_width = 512, 704
 downscale_factor = 2 / 3
 num_frames = 121
 
 # Part 1. Generate video at smaller resolution
 downscaled_height, downscaled_width = int(expected_height * downscale_factor), int(expected_width * downscale_factor)
+downscaled_height, downscaled_width = round_to_nearest_resolution_acceptable_by_vae(downscaled_height, downscaled_width)
 latents = pipe(
     conditions=None,
     prompt=prompt,
@@ -200,6 +206,11 @@ pipe.to("cuda")
 pipe_upsample.to("cuda")
 pipe.vae.enable_tiling()
 
+def round_to_nearest_resolution_acceptable_by_vae(height, width):
+    height = height - (height % pipe.vae_spatial_compression_ratio)
+    width = width - (width % pipe.vae_spatial_compression_ratio)
+    return height, width
+
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png")
 video = [image]
 condition1 = LTXVideoCondition(video=video, frame_index=0)
@@ -254,7 +265,6 @@ video = pipe(
 video = [frame.resize((expected_width, expected_height)) for frame in video]
 
 export_to_video(video, "output.mp4", fps=24)
-
 ```
 
 ### For video-to-video: 
@@ -272,8 +282,8 @@ pipe_upsample.to("cuda")
 pipe.vae.enable_tiling()
 
 def round_to_nearest_resolution_acceptable_by_vae(height, width):
-    height = height - (height % pipe.vae_temporal_compression_ratio)
-    width = width - (width % pipe.vae_temporal_compression_ratio)
+    height = height - (height % pipe.vae_spatial_compression_ratio)
+    width = width - (width % pipe.vae_spatial_compression_ratio)
     return height, width
 
 video = load_video(
@@ -331,7 +341,6 @@ video = pipe(
 video = [frame.resize((expected_width, expected_height)) for frame in video]
 
 export_to_video(video, "output.mp4", fps=24)
-
 ```