Merge branch 'new-image-text-tasks' of https://github.com/huggingface/huggingface.js into new-image-text-tasks

Author: apolinario

packages/tasks/src/tasks/image-text-to-video/about.md

@@ -6,11 +6,11 @@ Image-text-to-video models can be used to animate still images based on text des
 
 ### Dynamic Content Creation
 
-Transform static images into dynamic video content by adding motion, transformations, or effects described in text prompts. This is useful for creating engaging social media content, presentations, or marketing materials.
+Transform images into video by adding motion, transformations, or effects described in text prompts. This is useful for creating engaging social media content, presentations, or marketing materials.
 
 ### Guided Video Generation
 
-Use a reference image along with text prompts to guide the video generation process. This provides more control over the visual style and composition compared to text-to-video models alone.
+Use a reference image with text prompts to guide the video generation process. This provides more control over the visual style and composition compared to text-to-video models alone.
 
 ### Story Visualization
 
@@ -36,7 +36,7 @@ Models that perform specific video transformations based on text conditions, suc
 
 ## Inference
 
-You can use the Diffusers library to interact with image-text-to-video models.
+You can use the Diffusers library to interact with image-text-to-video models. Here's example snippet to use `LTXImageToVideoPipeline`.
 
 ```python
 import torch

packages/tasks/src/tasks/image-text-to-video/data.ts

@@ -46,7 +46,7 @@ const taskData: TaskDataCustom = {
 		},
 	],
 	summary:
-		"Image-text-to-video models take an image and a text prompt as input and generate a video based on the reference image and text instructions. These models are useful for animating still images, creating dynamic content from static references, and generating videos with specific motion or transformation guidance.",
+		"Image-text-to-video models take an reference image and a text instructions as and generate a video based on them. These models are useful for animating still images, creating dynamic content from static references, and generating videos with specific motion or transformation guidance.",
 	widgetModels: ["Lightricks/LTX-Video"],
 	youtubeId: undefined,
 };