diff --git a/packages/alibaba-video/README.md b/packages/alibaba-video/README.md
new file mode 100644
index 00000000..c82babb3
--- /dev/null
+++ b/packages/alibaba-video/README.md
@@ -0,0 +1,99 @@
+# @hypit/alibaba-video
+
+Alibaba Video Generation Model Support for Hypit
+
+## Overview
+
+This package provides integration with Alibaba's video generation models, specifically the **Qwen Video Generation (Qwen VVG)** model. It enables AI-powered video generation with text prompts and optional reference images.
+
+## Features
+
+- **Text-to-Video Generation**: Generate videos from text prompts
+- **Reference-Based Generation**: Use reference images to guide the generation style
+- **Configurable Resolution**: Support for 480p, 720p, and 1080p output
+- **Multiple Aspect Ratios**: Support for 1:1, 16:9, 9:16, 4:3, 3:4 formats
+- **Variable Duration**: Generate videos with 5-10 second duration
+
+## Supported Models
+
+### Alibaba Qwen Video Generation (alibaba-qwen-vvg)
+
+- **Input**: Text prompt (max 200 characters)
+- **Resolution**: 480p, 720p, 1080p
+- **Duration**: 5-10 seconds
+- **Aspect Ratios**: 1:1, 16:9, 9:16, 4:3, 3:4
+- **Optional Reference**: Image for style guidance
+
+## Usage
+
+### Basic Text-to-Video
+
+```markup
+<alibaba:TextVideo
+  id="my-video"
+  model="qwen-vvg"
+  prompt={description}
+  duration="6"
+  resolution="720p"
+  aspect-ratio="16:9"
+/>
+```
+
+### Video Generation with Reference Image
+
+```markup
+<alibaba:ReferenceVideo
+  id="styled-video"
+  model="qwen-vvg"
+  prompt={description}
+  duration="8"
+  resolution="1080p"
+  aspect-ratio="9:16"
+  reference-image={style.image}
+/>
+```
+
+## Configuration
+
+### Prompt
+- Maximum 200 characters
+- Should describe the desired video content clearly
+
+### Duration
+- Range: 5-10 seconds
+- Must be a whole number
+
+### Resolution
+- `480p`: Lower quality, faster generation
+- `720p`: Standard quality (default)
+- `1080p`: High quality, longer generation time
+
+### Aspect Ratio
+- `16:9`: Landscape (default)
+- `9:16`: Portrait/vertical
+- `1:1`: Square
+- `4:3`: Standard
+- `3:4`: Vertical standard
+
+## Architecture
+
+The package follows Hypit's standard model integration pattern:
+
+- **Generation Ports**: Defines input/output structure
+- **Markup Surfaces**: Provides XML/markup interface for video generation
+- **Fragment Builders**: Creates generation fragments with proper request sealing
+- **Surface Decoders**: Converts markup into generation requests
+
+## Dependencies
+
+- `@hypit/artifact`: Artifact type definitions
+- `@hypit/generation`: Generation request/port infrastructure
+- `@hypit/model-kit`: Model module definition utilities
+- `@hypit/markup`: Markup surface definitions
+- `@hypit/elaborator`: Fragment building and activation context
+- `@hypit/text`: Text type definitions
+- `@hypit/protocol`: Core protocol definitions
+
+## License
+
+See LICENSE file in the repository root.
diff --git a/packages/alibaba-video/package.json b/packages/alibaba-video/package.json
new file mode 100644
index 00000000..b968bfb7
--- /dev/null
+++ b/packages/alibaba-video/package.json
@@ -0,0 +1,22 @@
+{
+  "name": "@hypit/alibaba-video",
+  "version": "0.0.0-dev",
+  "license": "SEE LICENSE IN LICENSE",
+  "private": true,
+  "type": "module",
+  "exports": {
+    ".": "./src/index.ts"
+  },
+  "hypit": {
+    "activation": "./src/activation.ts"
+  },
+  "dependencies": {
+    "@hypit/artifact": "workspace:*",
+    "@hypit/elaborator": "workspace:*",
+    "@hypit/generation": "workspace:*",
+    "@hypit/model-kit": "workspace:*",
+    "@hypit/protocol": "workspace:*",
+    "@hypit/text": "workspace:*",
+    "@hypit/markup": "workspace:*"
+  }
+}
diff --git a/packages/alibaba-video/src/activation.ts b/packages/alibaba-video/src/activation.ts
new file mode 100644
index 00000000..098605f3
--- /dev/null
+++ b/packages/alibaba-video/src/activation.ts
@@ -0,0 +1,24 @@
+/**
+ * Alibaba Video Generation Model Activation
+ * Registers the model and surfaces with the Hypit system
+ */
+
+import type { ActivationContext } from "@hypit/elaborator";
+import {
+  alibabaVideoComponent,
+  alibabaVideoManifest,
+  alibabaVideoMarkupSurfaces,
+} from "./index.js";
+
+export function activate(context: ActivationContext) {
+  // Register the model component
+  context.component(alibabaVideoComponent);
+
+  // Register the manifest
+  context.manifest(alibabaVideoManifest);
+
+  // Register all markup surfaces
+  for (const surface of alibabaVideoMarkupSurfaces) {
+    context.surface(surface);
+  }
+}
diff --git a/packages/alibaba-video/src/fragment.ts b/packages/alibaba-video/src/fragment.ts
new file mode 100644
index 00000000..46305571
--- /dev/null
+++ b/packages/alibaba-video/src/fragment.ts
@@ -0,0 +1,38 @@
+/**
+ * Alibaba Video Generation Fragment Builders
+ * Provides functions to create generation fragments for video generation requests
+ */
+
+import type { AssembledGenerationFragment, GenerationFragment } from "@hypit/elaborator";
+import {
+  createAssembledGenerationFragment,
+  createGenerationFragment,
+} from "@hypit/elaborator";
+import {
+  alibabaVideoEndpoints,
+  sealAlibabaVideoRequest,
+  type AlibabaVideoPortMap,
+} from "./index.js";
+
+/**
+ * Creates an assembled generation fragment for Alibaba video generation
+ * with resolved media bindings and draft type information
+ */
+export function createAlibabaVideoAssembledGenerationFragment(
+  ports: AlibabaVideoPortMap
+): AssembledGenerationFragment {
+  const endpoint = alibabaVideoEndpoints.qwenVvg!;
+  const request = sealAlibabaVideoRequest("alibaba-qwen-vvg", ports);
+  return createAssembledGenerationFragment(endpoint, request);
+}
+
+/**
+ * Creates a generation fragment for Alibaba video generation
+ */
+export function createAlibabaVideoGenerationFragment(
+  ports: AlibabaVideoPortMap
+): GenerationFragment {
+  const endpoint = alibabaVideoEndpoints.qwenVvg!;
+  const request = sealAlibabaVideoRequest("alibaba-qwen-vvg", ports);
+  return createGenerationFragment(endpoint, request);
+}
diff --git a/packages/alibaba-video/src/index.ts b/packages/alibaba-video/src/index.ts
new file mode 100644
index 00000000..034e568c
--- /dev/null
+++ b/packages/alibaba-video/src/index.ts
@@ -0,0 +1,255 @@
+import { artifactTypes } from "@hypit/artifact";
+import {
+  sealGenerationPortRequest,
+  sealGenerationPortTable,
+} from "@hypit/generation";
+import type {
+  GenerationPortTable,
+  GenerationPortValue,
+  GenerationRequest,
+} from "@hypit/generation";
+import type {
+  SurfaceAttributeVocabulary,
+  SurfacePortVocabulary,
+  SurfaceVocabulary,
+} from "@hypit/markup";
+import { defineExactModelModule } from "@hypit/model-kit";
+import { textTypes } from "@hypit/text";
+
+/**
+ * Alibaba Video Generation Models
+ * Supports:
+ * - alibaba-qwen-vvg: Qwen Video Generation model
+ */
+export const alibabaVideoModuleRef = {
+  name: "@hypit/alibaba-video",
+  version: "1",
+} as const;
+
+export const alibabaVideoModels = [
+  "alibaba-qwen-vvg",
+] as const;
+export type AlibabaVideoModel = typeof alibabaVideoModels[number];
+
+const ASPECT_RATIOS = [
+  "1:1",
+  "16:9",
+  "9:16",
+  "4:3",
+  "3:4",
+] as const;
+
+const RESOLUTIONS = [
+  "480p",
+  "720p",
+  "1080p",
+] as const;
+
+/**
+ * Alibaba Video Generation model ports configuration.
+ * Defines the input/output structure for video generation requests.
+ */
+function alibabaVideoPortTable(
+  model: AlibabaVideoModel
+): GenerationPortTable {
+  return sealGenerationPortTable({
+    model,
+    result: "video",
+    ports: [
+      {
+        name: "prompt",
+        value: { kind: "text", maxChars: 200 },
+        minItems: 1,
+        maxItems: 1,
+      },
+      {
+        name: "duration",
+        value: { kind: "number", integer: true, minimum: 5, maximum: 10 },
+        minItems: 1,
+        maxItems: 1,
+      },
+      {
+        name: "resolution",
+        value: {
+          kind: "enum",
+          values: [...RESOLUTIONS],
+        },
+        minItems: 0,
+        maxItems: 1,
+      },
+      {
+        name: "aspectRatio",
+        value: { kind: "enum", values: [...ASPECT_RATIOS] },
+        minItems: 0,
+        maxItems: 1,
+      },
+      {
+        name: "referenceImage",
+        value: { kind: "media", accepts: ["image"] },
+        minItems: 0,
+        maxItems: 1,
+      },
+    ],
+    requires: [
+      { kind: "atMostOneOf", ports: ["referenceImage"] },
+    ],
+  });
+}
+
+export const alibabaVideoPorts: Readonly<
+  Record<AlibabaVideoModel, GenerationPortTable>
+> = {
+  "alibaba-qwen-vvg": alibabaVideoPortTable("alibaba-qwen-vvg"),
+};
+
+export type AlibabaVideoPortMap = Readonly<
+  Record<string, readonly GenerationPortValue[]>
+>;
+
+export function sealAlibabaVideoRequest(
+  model: AlibabaVideoModel,
+  ports: AlibabaVideoPortMap
+): GenerationRequest {
+  return sealGenerationPortRequest(alibabaVideoPorts[model], ports);
+}
+
+const alibabaVideoBaseDefinition = defineExactModelModule({
+  module: alibabaVideoModuleRef,
+  endpoints: [
+    {
+      key: "qwen-vvg",
+      requestTypeName: "AlibabaQwenVVGRequest",
+      producerName: "request-alibaba-qwen-vvg",
+      ports: alibabaVideoPorts["alibaba-qwen-vvg"],
+    },
+  ],
+});
+
+export const alibabaVideoEndpoints = alibabaVideoBaseDefinition.endpoints;
+export const alibabaVideoComponent = alibabaVideoBaseDefinition.component;
+
+const alibabaVideoCommonAttributes: readonly SurfaceAttributeVocabulary[] = [
+  {
+    name: "id",
+    kind: "identifier",
+    required: true,
+    summary: "Names this generation and prefixes the binding it publishes.",
+  },
+  {
+    name: "model",
+    kind: "literal",
+    required: true,
+    summary: "Chooses the exact Alibaba video model that renders the video.",
+    values: ["qwen-vvg", "alibaba-qwen-vvg"],
+  },
+  {
+    name: "prompt",
+    kind: "reference",
+    required: true,
+    summary: "The Text description for the video generation (max 200 characters).",
+    accepts: [textTypes.text],
+  },
+  {
+    name: "duration",
+    kind: "literal",
+    required: true,
+    summary: "Sets the length of the video in seconds (5-10 seconds).",
+  },
+  {
+    name: "resolution",
+    kind: "literal",
+    required: false,
+    summary: "Chooses the output resolution of the video.",
+    values: [...RESOLUTIONS],
+  },
+  {
+    name: "aspect-ratio",
+    kind: "literal",
+    required: false,
+    summary: "Chooses the aspect ratio of the generated video.",
+    values: [...ASPECT_RATIOS],
+  },
+];
+
+const alibabaVideoPort: readonly SurfacePortVocabulary[] = [
+  {
+    name: "video",
+    type: artifactTypes.blob,
+    summary: "The generated video Artifact.",
+  },
+];
+
+const alibabaVideoSettingNotes: readonly string[] = [
+  "`duration` must be between 5 and 10 seconds.",
+  "`resolution` defaults to `720p`.",
+  "`aspect-ratio` defaults to `16:9`.",
+  "Prompt text is limited to 200 characters maximum.",
+];
+
+export const alibabaVideoMarkupSurfaces = [
+  {
+    name: "text-video",
+    tag: "TextVideo",
+    mode: "structured",
+    outputs: Object.values(alibabaVideoEndpoints).flatMap((endpoint) => [
+      endpoint.draftType,
+      ...Object.values(endpoint.mediaBindings).map((binding) => binding.type),
+    ]),
+    vocabulary: {
+      summary:
+        "Generates one video with Alibaba Qwen video model from a Text prompt alone.",
+      attributes: alibabaVideoCommonAttributes,
+      ports: alibabaVideoPort,
+      example:
+        '<alibaba:TextVideo id="scene" model="qwen-vvg" prompt={description} duration="5" resolution="720p" aspect-ratio="16:9"/>',
+      notes: [
+        ...alibabaVideoSettingNotes,
+        "The element accepts no children and no text content.",
+      ],
+    } as SurfaceVocabulary,
+  },
+  {
+    name: "reference-video",
+    tag: "ReferenceVideo",
+    mode: "structured",
+    outputs: Object.values(alibabaVideoEndpoints).flatMap((endpoint) => [
+      endpoint.draftType,
+      ...Object.values(endpoint.mediaBindings).map((binding) => binding.type),
+    ]),
+    vocabulary: {
+      summary:
+        "Generates one video with Alibaba Qwen model from a Text prompt and an optional reference image.",
+      attributes: [
+        ...alibabaVideoCommonAttributes,
+        {
+          name: "reference-image",
+          kind: "reference",
+          required: false,
+          summary:
+            "The image Artifact to use as a style or content reference for video generation.",
+          accepts: [artifactTypes.blob],
+        },
+      ],
+      ports: alibabaVideoPort,
+      example:
+        '<alibaba:ReferenceVideo id="styled-scene" model="qwen-vvg" prompt={description} duration="6" resolution="1080p" aspect-ratio="9:16" reference-image={style.image}/>',
+      notes: [
+        ...alibabaVideoSettingNotes,
+        "Reference image is optional and provides style guidance.",
+        "The element accepts no children and no text content.",
+      ],
+    } as SurfaceVocabulary,
+  },
+] as const;
+
+export const alibabaVideoManifest = alibabaVideoBaseDefinition.manifest;
+export const alibabaVideoDefinition = alibabaVideoBaseDefinition;
+
+export {
+  createAlibabaVideoAssembledGenerationFragment,
+  createAlibabaVideoGenerationFragment,
+} from "./fragment.js";
+export {
+  decodeAlibabaVideoTextVideoSurface,
+  decodeAlibabaVideoReferenceVideoSurface,
+} from "./surface.js";
diff --git a/packages/alibaba-video/src/surface.ts b/packages/alibaba-video/src/surface.ts
new file mode 100644
index 00000000..e7c879ef
--- /dev/null
+++ b/packages/alibaba-video/src/surface.ts
@@ -0,0 +1,41 @@
+/**
+ * Alibaba Video Generation Surface Decoders
+ * Decodes markup surfaces into generation requests and port configurations
+ */
+
+import type { Surface } from "@hypit/markup";
+import { createAlibabaVideoGenerationFragment } from "./fragment.js";
+import type { AlibabaVideoPortMap } from "./index.js";
+
+/**
+ * Decodes Alibaba TextVideo surface markup into a generation fragment
+ */
+export function decodeAlibabaVideoTextVideoSurface(
+  surface: Surface
+): ReturnType<typeof createAlibabaVideoGenerationFragment> {
+  const ports: AlibabaVideoPortMap = {
+    prompt: surface.getAttribute("prompt") as any,
+    duration: surface.getAttribute("duration") as any,
+    resolution: surface.getAttribute("resolution") as any,
+    aspectRatio: surface.getAttribute("aspect-ratio") as any,
+  };
+
+  return createAlibabaVideoGenerationFragment(ports);
+}
+
+/**
+ * Decodes Alibaba ReferenceVideo surface markup into a generation fragment
+ */
+export function decodeAlibabaVideoReferenceVideoSurface(
+  surface: Surface
+): ReturnType<typeof createAlibabaVideoGenerationFragment> {
+  const ports: AlibabaVideoPortMap = {
+    prompt: surface.getAttribute("prompt") as any,
+    duration: surface.getAttribute("duration") as any,
+    resolution: surface.getAttribute("resolution") as any,
+    aspectRatio: surface.getAttribute("aspect-ratio") as any,
+    referenceImage: surface.getAttribute("reference-image") as any,
+  };
+
+  return createAlibabaVideoGenerationFragment(ports);
+}