Update README.md

README.md

@@ -198,7 +198,7 @@ export_to_video(video, "output.mp4", fps=24)
 import torch
 from diffusers import LTXConditionPipeline, LTXLatentUpsamplePipeline
 from diffusers.pipelines.ltx.pipeline_ltx_condition import LTXVideoCondition
-from diffusers.utils import export_to_video, load_image
+from diffusers.utils import export_to_video, load_image, load_video
 
 pipe = LTXConditionPipeline.from_pretrained("Lightricks/LTX-Video-0.9.7-dev", torch_dtype=torch.bfloat16)
 pipe_upsample = LTXLatentUpsamplePipeline.from_pretrained("Lightricks/ltxv-spatial-upscaler-0.9.7", vae=pipe.vae, torch_dtype=torch.bfloat16)
@@ -212,12 +212,12 @@ def round_to_nearest_resolution_acceptable_by_vae(height, width):
     return height, width
 
 image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/penguin.png")
-video = [image]
+video = load_video(export_to_video([image])) # compress the image using video compression as the model was trained on videos
 condition1 = LTXVideoCondition(video=video, frame_index=0)
 
-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."
+prompt = "A cute little penguin takes out a book and starts reading it"
 negative_prompt = "worst quality, inconsistent motion, blurry, jittery, distorted"
-expected_height, expected_width = 832, 480
+expected_height, expected_width = 480, 832
 downscale_factor = 2 / 3
 num_frames = 96