[DOCS] LTX Video Generation Docs

site/docs/use-cases/video-generation/_sections/_run_model/_text2video_cpp.mdx

@@ -0,0 +1,16 @@
+import CodeBlock from '@theme/CodeBlock';
+
+<CodeBlock language="cpp" showLineNumbers>
+{`#include "openvino/genai/video_generation/text2video_pipeline.hpp"
+#include "imwrite_video.hpp"
+
+int main(int argc, char* argv[]) {
+    const std::string models_path = argv[1], prompt = argv[2];
+
+    ov::genai::Text2VideoPipeline pipe(models_path, "${props.device || 'CPU'}");
+    ov::Tensor video = pipe.generate(prompt).video;
+
+    imwrite_video("genai_video.avi", video);
+}
+`}
+</CodeBlock>

site/docs/use-cases/video-generation/_sections/_run_model/_text2video_python.mdx

@@ -0,0 +1,33 @@
+import CodeBlock from '@theme/CodeBlock';
+
+<CodeBlock language="python" showLineNumbers>
+{`import openvino_genai as ov_genai
+import cv2
+
+def save_video(filename: str, video_tensor, fps: int = 25):
+    batch_size, num_frames, height, width, _ = video_tensor.shape
+    video_data = video_tensor.data
+
+    for b in range(batch_size):
+        if batch_size == 1:
+            output_path = filename
+        else:
+            base, ext = filename.rsplit(".", 1) if "." in filename else (filename, "avi")
+            output_path = f"{base}_b{b}.{ext}"
+
+        fourcc = cv2.VideoWriter_fourcc(*"MJPG")
+        writer = cv2.VideoWriter(output_path, fourcc, fps, (width, height))
+
+        for f in range(num_frames):
+            writer.write(video_data[b, f])
+
+        writer.release()
+        print(f"Wrote {output_path} ({num_frames} frames, {width}x{height} @ {fps} fps)")
+
+
+pipe = ov_genai.Text2VideoPipeline(model_path, "${props.device || 'CPU'}")
+video = pipe.generate(prompt).video
+
+save_video("genai_video.avi", video)
+`}
+</CodeBlock>

site/docs/use-cases/video-generation/_sections/_run_model/index.mdx

@@ -0,0 +1,36 @@
+import Text2VideoCPP from './_text2video_cpp.mdx';
+import Text2VideoPython from './_text2video_python.mdx';
+
+## Run Model Using OpenVINO GenAI
+
+OpenVINO GenAI supports the following video generation pipeline:
+- [`Text2VideoPipeline`](https://docs.openvino.ai/2026/api/genai_api/_autosummary/openvino_genai.Text2VideoPipeline.html) for creating videos from text prompts.
+
+<LanguageTabs>
+    <TabItemPython>
+        <Tabs groupId="device">
+            <TabItem label="CPU" value="cpu">
+                <Text2VideoPython device="CPU" />
+            </TabItem>
+            <TabItem label="GPU" value="gpu">
+                <Text2VideoPython device="GPU" />
+            </TabItem>
+        </Tabs>
+    </TabItemPython>
+    <TabItemCpp>
+        <Tabs groupId="device">
+            <TabItem label="CPU" value="cpu">
+                <Text2VideoCPP device="CPU" />
+            </TabItem>
+            <TabItem label="GPU" value="gpu">
+                <Text2VideoCPP device="GPU" />
+            </TabItem>
+        </Tabs>
+    </TabItemCpp>
+</LanguageTabs>
+
+:::tip
+
+Use CPU or GPU as devices without any other code change.
+
+:::

site/docs/use-cases/video-generation/_sections/_usage_options/index.mdx

@@ -0,0 +1,83 @@
+import GenerationConfigurationWorkflow from '@site/docs/use-cases/_shared/_generation_configuration_workflow.mdx';
+
+## Additional Usage Options
+
+:::tip
+Check out [Python](https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/python/video_generation) and [C++](https://github.com/openvinotoolkit/openvino.genai/tree/master/samples/cpp/video_generation) video generation samples.
+:::
+
+### Use Different Generation Parameters
+
+<GenerationConfigurationWorkflow />
+
+#### Video Generation Configuration
+
+You can adjust several parameters to control the video generation process, including dimensions and the number of inference steps:
+
+<LanguageTabs>
+    <TabItemPython>
+        ```python
+        import openvino_genai as ov_genai
+
+        pipe = ov_genai.Text2VideoPipeline(model_path, "CPU")
+        fps = 25
+        video = pipe.generate(
+          prompt,
+          # highlight-start
+          width=512,
+          height=512,
+          num_videos_per_prompt=1,
+          num_inference_steps=30,
+          num_frames=161,
+          guidance_scale=7.5,
+          frame_rate=fps
+          # highlight-end
+        ).video
+
+        save_video("genai_video.avi", video, fps)
+        ```
+    </TabItemPython>
+    <TabItemCpp>
+        ```cpp
+        #include "openvino/genai/video_generation/text2video_pipeline.hpp"
+        #include "imwrite_video.hpp"
+
+        int main(int argc, char* argv[]) {
+            const std::string models_path = argv[1], prompt = argv[2];
+
+            ov::genai::Text2VideoPipeline pipe(models_path, "CPU");
+            float fps = 25;
+            ov::Tensor video = pipe.generate(
+                prompt,
+                // highlight-start
+                ov::genai::width(512),
+                ov::genai::height(512),
+                ov::genai::num_videos_per_prompt(1),
+                ov::genai::num_inference_steps(30),
+                ov::genai::num_frames(161),
+                ov::genai::guidance_scale(7.5f),
+                ov::genai::frame_rate(fps)
+                // highlight-end
+            ).video;
+
+            imwrite_video("genai_video.avi", video, fps);
+        }
+        ```
+    </TabItemCpp>
+</LanguageTabs>
+
+:::info Understanding Video Generation Parameters
+
+- `negative_prompt`: Negative prompt for video(s) generation.
+- `width`: The width of resulting video(s).
+- `height`: The height of resulting video(s).
+- `num_frames`: Number of frames to generate for each video. Higher values produce longer videos but increase compute and memory.
+- `num_videos_per_prompt`: Specifies how many video variations to generate in a single request for the same prompt.
+- `num_inference_steps`: Defines denoising iteration count. Higher values increase quality and generation time, lower values generate faster with less detail.
+- `guidance_scale`: Balances prompt adherence vs. creativity. Higher values follow prompt more strictly, lower values allow more creative freedom.
+- `generator`: Controls randomness for reproducible results. Same generator seed produces identical videos across runs.
+- `frame_rate`: Target video FPS used by the pipeline.
+
+For the full list of generation parameters, refer to the [Video Generation Config API](https://docs.openvino.ai/2026/api/genai_api/_autosummary/openvino_genai.VideoGenerationConfig.html).
+
+:::

site/docs/use-cases/video-generation/index.mdx

@@ -0,0 +1,31 @@
+---
+sidebar_position: 3
+---
+import OptimumCLI from '@site/src/components/OptimumCLI';
+import ConvertModelSection from '../_shared/_convert_model.mdx';
+import RunModelSection from './_sections/_run_model/index.mdx';
+import UsageOptionsSection from './_sections/_usage_options/index.mdx';
+
+# Video Generation Using Diffusers
+
+## LTX-Video Pipeline for Video Generation
+
+LTX-Video is the DiT-based video generation model capable of generating high-quality videos.
+This video generation pipeline turns a text prompt into a sequence of video frames:
+1. **Prompt → tokens**: the prompt is tokenized (and padded to the model’s max length).
+2. **Tokens → text embeddings**: a text encoder produces embeddings used to condition generation.
+3. **Denoising loop**: a Transformer predicts and refines video latents over multiple steps, while the scheduler controls the noise level at each step.
+4. **Latents → frames**: the final latents are decoded into RGB video frames.
+
+![LTX Pipeline Workflow](/img/ltx-pipeline.png)
+*Source: [arXiv:2501.00103](https://arxiv.org/abs/2501.00103)*
+
+<ConvertModelSection>
+    Download and convert LTX model [Lightricks/LTX-Video](https://huggingface.co/Lightricks/LTX-Video) to OpenVINO format from Hugging Face:
+
+    <OptimumCLI model='Lightricks/LTX-Video' outputDir='LTX_Video_ov' weightFormat='int8' trustRemoteCode />
+</ConvertModelSection>
+
+<RunModelSection />
+
+<UsageOptionsSection />

site/src/pages/_sections/UseCasesSection/components/video-generation.tsx

@@ -0,0 +1,36 @@
+import Button from '@site/src/components/Button';
+import { LanguageTabs, TabItemCpp, TabItemPython } from '@site/src/components/LanguageTabs';
+
+import UseCaseCard from './UseCaseCard';
+
+import CodeExampleCpp from '@site/docs/use-cases/video-generation/_sections/_run_model/_text2video_cpp.mdx';
+import CodeExamplePython from '@site/docs/use-cases/video-generation/_sections/_run_model/_text2video_python.mdx';
+
+export const VideoGeneration = () => (
+  <UseCaseCard>
+    <UseCaseCard.Title>Video Generation Using Diffusers</UseCaseCard.Title>
+    <UseCaseCard.Description>
+      Create videos with LTX-Video model using a diffusion-based generation pipeline
+      to produce high-quality clips for creative storytelling, marketing content, product demos, and rapid visual prototyping.
+    </UseCaseCard.Description>
+    <UseCaseCard.Features>
+      <li>Support for text-to-video pipeline</li>
+      <li>Control video generation by adjusting parameters (dimensions, iterations, etc.)</li>
+      <li>Generate videos per one request</li>
+    </UseCaseCard.Features>
+    <UseCaseCard.Code>
+      <LanguageTabs>
+        <TabItemPython>
+          <CodeExamplePython />
+        </TabItemPython>
+        <TabItemCpp>
+          <CodeExampleCpp />
+        </TabItemCpp>
+      </LanguageTabs>
+    </UseCaseCard.Code>
+    <UseCaseCard.Actions>
+      <Button label="Explore Use Case" link="docs/use-cases/video-generation" variant="primary" />
+      <Button label="View Code Samples" link="docs/samples" variant="primary" outline />
+    </UseCaseCard.Actions>
+  </UseCaseCard>
+);

site/src/pages/_sections/UseCasesSection/index.tsx

@@ -10,6 +10,7 @@ import { SpeechRecognition } from './components/speech-recognition';
 import { TextGeneration } from './components/text-generation';
 import { TextRerank } from './components/text-rerank';
 import { TextEmbedding } from './components/text-embedding';
+import { VideoGeneration } from './components/video-generation';
 
 export const UseCasesSection = () => (
   <section className={styles.useCasesSection}>
@@ -24,6 +25,7 @@ export const UseCasesSection = () => (
       <SpeechGeneration />
       <TextEmbedding />
       <TextRerank />
+      <VideoGeneration />
     </div>
     <div className={styles.useCasesFooter}>
       <strong>Looking for more?</strong>&nbsp;See all{' '}