Add LTX-2 Documentation

docs.json

@@ -197,7 +197,13 @@
                   {
                     "group": "Video",
                     "pages": [
-                      "tutorials/video/ltxv",
+                      {
+                        "group": "LTX",
+                        "pages": [
+                          "tutorials/video/ltxv",
+                          "tutorials/video/ltx/ltx-2"
+                        ]
+                      },
                       {
                         "group": "Wan Video",
                         "pages": [
@@ -864,7 +870,13 @@
                   {
                     "group": "视频",
                     "pages": [
-                      "zh-CN/tutorials/video/ltxv",
+                      {
+                        "group": "LTX",
+                        "pages": [
+                          "zh-CN/tutorials/video/ltxv",
+                          "zh-CN/tutorials/video/ltx/ltx-2"
+                        ]
+                      },
                       {
                         "group": "万相视频",
                         "pages": [

tutorials/video/ltx/ltx-2.mdx

@@ -0,0 +1,132 @@
+---
+title: "LTX-2"
+description: "A DiT-based audio-video foundation model for synchronized video and audio generation"
+---
+
+import UpdateReminder from "/snippets/tutorials/update-reminder.mdx";
+
+[LTX-2](https://huggingface.co/Lightricks/LTX-2) is a 19B parameter DiT-based audio-video foundation model by Lightricks. It generates synchronized video and audio in a single pass, creating cohesive experiences where motion, dialogue, background noise, and music are produced together.
+
+<UpdateReminder/>
+
+## Key features
+
+- **Synchronized audio-video generation**: Generates motion, dialogue, SFX, and music together in one pass
+- **Multiple generation modes**: Text-to-video, image-to-video, and video-to-video
+- **Control options**: Canny, Depth, and Pose video-to-video control via IC-LoRAs
+- **Keyframe-driven generation**: Interpolate between keyframe images
+- **Native upscaling**: Spatial (2x) and temporal (2x) upscalers for higher resolution and FPS
+- **Prompt enhancement**: Automatic prompt enhancement support
+
+## Model checkpoints
+
+| Name | Description |
+|------|-------------|
+| ltx-2-19b-dev | Full model in bf16, flexible and trainable |
+| ltx-2-19b-dev-fp8 | Full model in fp8 quantization |
+| ltx-2-19b-distilled | Distilled version, 8 steps, CFG=1 |
+| ltx-2-spatial-upscaler-x2-1.0 | 2x spatial upscaler for higher resolution |
+| ltx-2-temporal-upscaler-x2-1.0 | 2x temporal upscaler for higher FPS |
+
+## Getting started
+
+LTX-2 is natively supported in ComfyUI. To get started:
+
+1. Update ComfyUI to the latest version
+2. Go to **Template Library** > **Video** > choose any LTX-2 workflow
+3. Follow the pop-up to download models and run the workflow
+
+## Workflows
+
+### Text-to-video
+
+Generate videos from text prompts.
+
+<CardGroup cols={2}>
+  <Card title="Text-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_t2v.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_t2v&utm_source=docs&utm_campaign=ltx_2">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+**Distilled version** (faster, 8 steps):
+<Card title="Text-to-Video Distilled" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_t2v_distilled.json">
+  Download workflow
+</Card>
+
+### Image-to-video
+
+Generate videos from an input image.
+
+<CardGroup cols={2}>
+  <Card title="Image-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_i2v.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_i2v&utm_source=docs&utm_campaign=ltx_2">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+**Distilled version** (faster, 8 steps):
+<Card title="Image-to-Video Distilled" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_i2v_distilled.json">
+  Download workflow
+</Card>
+
+### Control-to-video
+
+Generate videos with structural control using IC-LoRAs.
+
+**Depth control:**
+<CardGroup cols={2}>
+  <Card title="Depth-to-Video" icon="download" href="https://github.com/Comfy-Org/workflow_templates/raw/refs/heads/main/templates/video_ltx2_depth_to_video.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_depth_to_video&utm_source=docs&utm_campaign=ltx_2">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+**Canny control:**
+<CardGroup cols={2}>
+  <Card title="Canny-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_canny_to_video.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_canny_to_video&utm_source=docs&utm_campaign=ltx_2">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+**Pose control:**
+<CardGroup cols={2}>
+  <Card title="Pose-to-Video" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_pose_to_video.json">
+    Download workflow
+  </Card>
+  <Card title="Run on Comfy Cloud" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_pose_to_video&utm_source=docs&utm_campaign=ltx_2">
+    Open in cloud
+  </Card>
+</CardGroup>
+
+## Prompting tips
+
+When writing prompts for LTX-2, focus on detailed, chronological descriptions of actions and scenes. Include specific movements, appearances, camera angles, and environmental details in a single flowing paragraph. Start directly with the action and keep descriptions literal and precise.
+
+Structure your prompts with:
+- Main action in a single sentence
+- Specific details about movements and gestures
+- Character/object appearances
+- Background and environment details
+- Camera angles and movements
+- Lighting and colors
+- Any changes or sudden events
+
+Keep prompts within 200 words for best results.
+
+## Resources
+
+- [GitHub Repository](https://github.com/Lightricks/LTX-2)
+- [Hugging Face Model](https://huggingface.co/Lightricks/LTX-2)
+- [LTX-2 Prompting Guide](https://ltx.video/blog/how-to-prompt-for-ltx-2)
+- [ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo/)
+

zh-CN/tutorials/video/ltx/ltx-2.mdx

@@ -0,0 +1,132 @@
+---
+title: "LTX-2"
+description: "基于 DiT 的音视频基础模型，支持同步生成视频和音频"
+---
+
+import UpdateReminder from "/snippets/zh/tutorials/update-reminder.mdx";
+
+[LTX-2](https://huggingface.co/Lightricks/LTX-2) 是 Lightricks 推出的 190 亿参数 DiT 音视频基础模型。它可以在单次生成中同步产出视频和音频，将动作、对话、背景音效和音乐融为一体。
+
+<UpdateReminder/>
+
+## 主要特性
+
+- **音视频同步生成**：一次生成动作、对话、音效和音乐
+- **多种生成模式**：支持文生视频、图生视频和视频转视频
+- **控制选项**：通过 IC-LoRAs 支持 Canny、Depth 和 Pose 视频控制
+- **关键帧驱动生成**：在关键帧图像之间进行插值
+- **原生放大**：空间 (2x) 和时间 (2x) 放大器，提升分辨率和帧率
+- **提示词增强**：支持自动提示词增强
+
+## 模型检查点
+
+| 名称 | 描述 |
+|------|------|
+| ltx-2-19b-dev | bf16 完整模型，灵活可训练 |
+| ltx-2-19b-dev-fp8 | fp8 量化完整模型 |
+| ltx-2-19b-distilled | 蒸馏版本，8 步，CFG=1 |
+| ltx-2-spatial-upscaler-x2-1.0 | 2x 空间放大器，提升分辨率 |
+| ltx-2-temporal-upscaler-x2-1.0 | 2x 时间放大器，提升帧率 |
+
+## 快速入门
+
+LTX-2 已原生支持 ComfyUI。开始使用：
+
+1. 将 ComfyUI 更新到最新版本
+2. 进入 **模板库** > **视频** > 选择任意 LTX-2 工作流
+3. 按照弹窗提示下载模型并运行工作流
+
+## 工作流
+
+### 文生视频
+
+从文本提示词生成视频。
+
+<CardGroup cols={2}>
+  <Card title="文生视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_t2v.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_t2v&utm_source=docs&utm_campaign=ltx_2">
+    在云端打开
+  </Card>
+</CardGroup>
+
+**蒸馏版本**（更快，8 步）：
+<Card title="文生视频蒸馏版" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_t2v_distilled.json">
+  下载工作流
+</Card>
+
+### 图生视频
+
+从输入图像生成视频。
+
+<CardGroup cols={2}>
+  <Card title="图生视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_i2v.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_i2v&utm_source=docs&utm_campaign=ltx_2">
+    在云端打开
+  </Card>
+</CardGroup>
+
+**蒸馏版本**（更快，8 步）：
+<Card title="图生视频蒸馏版" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_i2v_distilled.json">
+  下载工作流
+</Card>
+
+### 控制生成视频
+
+使用 IC-LoRAs 进行结构控制生成视频。
+
+**深度控制：**
+<CardGroup cols={2}>
+  <Card title="深度转视频" icon="download" href="https://github.com/Comfy-Org/workflow_templates/raw/refs/heads/main/templates/video_ltx2_depth_to_video.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_depth_to_video&utm_source=docs&utm_campaign=ltx_2">
+    在云端打开
+  </Card>
+</CardGroup>
+
+**Canny 边缘控制：**
+<CardGroup cols={2}>
+  <Card title="Canny 转视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_canny_to_video.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_canny_to_video&utm_source=docs&utm_campaign=ltx_2">
+    在云端打开
+  </Card>
+</CardGroup>
+
+**姿态控制：**
+<CardGroup cols={2}>
+  <Card title="姿态转视频" icon="download" href="https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/templates/video_ltx2_pose_to_video.json">
+    下载工作流
+  </Card>
+  <Card title="在 Comfy Cloud 运行" icon="cloud" href="https://cloud.comfy.org/?template=video_ltx2_pose_to_video&utm_source=docs&utm_campaign=ltx_2">
+    在云端打开
+  </Card>
+</CardGroup>
+
+## 提示词技巧
+
+编写 LTX-2 提示词时，请专注于详细、按时间顺序描述动作和场景。在一个连贯的段落中包含具体的动作、外观、镜头角度和环境细节。直接从动作开始，保持描述的字面性和精确性。
+
+提示词结构建议：
+- 用一句话描述主要动作
+- 动作和手势的具体细节
+- 角色/物体外观
+- 背景和环境细节
+- 镜头角度和运动
+- 光线和色彩
+- 任何变化或突发事件
+
+提示词最好控制在 200 词以内。
+
+## 资源
+
+- [GitHub 仓库](https://github.com/Lightricks/LTX-2)
+- [Hugging Face 模型](https://huggingface.co/Lightricks/LTX-2)
+- [LTX-2 提示词指南](https://ltx.video/blog/how-to-prompt-for-ltx-2)
+- [ComfyUI-LTXVideo](https://github.com/Lightricks/ComfyUI-LTXVideo/)
+