工作流 / 视频 / Kling2.6：文生视频（音画同步）

Kling2.6：文生视频（音画同步）

Kling2.6: Storytelling Videos with Audio

将你的故事转化为含对话、音乐、音效和环境音的视频

视频 3 个节点 27 次使用 ComfyUI ≥ 0.5.0 ComfyUI 4 KB

下载工作流 JSON 查看官方来源

下载后把文件拖进 ComfyUI 窗口即可打开。

节点构成

SaveVideo × 1

MarkdownNote × 1

KlingTextToVideoWithAudio × 1

官方标注的模型

KlingKling 2.6

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
  "id": "e840ec67-e4c6-480d-9ff1-63aee316553b",
  "revision": 0,
  "last_node_id": 10,
  "last_link_id": 5,
  "nodes": [
      {
          "id": 10,
          "type": "SaveVideo",
          "pos": [
              -810,
              860
          ],
          "size": [
              700,
              430
          ],
          "flags": [],
          "order": 2,
          "mode": 0,
          "inputs": [
              {
                  "name": "video",
                  "type": "VIDEO",
                  "link": 5
              }
          ],
          "outputs": [],
          "properties": [],
          "widgets_values": [
              "video/Kling2.6",
              "mp4",
              "h264"
          ]
      },
      {
          "id": 9,
          "type": "MarkdownNote",
          "pos": [
              -1890,
              860
          ],
          "size": [
              520,
              659.7916666666667
          ],
          "flags": [],
          "order": 0,
          "mode": 0,
          "inputs": [],
          "outputs": [],
          "title": "Prompt Format",
          "properties": [],
          "widgets_values": [
              "**Prompt Format** = **Scene** (Scene Description) + **Element** (Subject Description) + **Movement** (Movement Description) + **Audio**(Dialogue / Singing / Sound Effects / Pure Music) + **Other** (Style / Emotion / Camera)\n\n💡\n\n*   **Dialogue**: \"Sentence\" + Emotion + Speech Speed + Tone + Character Label\n    *   **Single Character**: Specify voice attributes (e.g., **[Man speaking]**, \"Sentence\" + Deep + Fast).\n    *   **Multiple Characters**: Use clear labels to distinguish (e.g., **[Character A, angrily]** says, \"Sentence\" **[Character B, calmly]** replies, \"Sentence\").\n\n*   **Singing**: \"Lyrics\" + **Singing Style** + Accompaniment Description + Emotion\n    *   **Style**: Pop, Opera, Country, etc.\n    *   **Emotion/Techniques**: **High-pitched, Vibrato, Gentle singing.**\n\n*   **Rap**: \"Sentence (Rhyming)\" + **Rhythm Style** + Emotion\n    *   **Rhythm Style**: **Intense Boom Bap, Trap Style Beat, Fast Flow.**\n    *   **Content**: \"Sentence\" should reflect **Rhyme and Meter.**\n\n*   **Sound Effects**: Sound Source (Action/Object) + State + **Professional Sound Effects**\n    *   **Structure**: [Object: Wooden Door] suddenly [Action: **Slams**] + [Sound Effect: **Bang**].\n    *   **Material/State: Glass Breaking, Metal Impact, Screeching Brakes.**\n\n*   **Ambient Sound**: Scene + **Sound Elements + Spatial Reverb**\n    *   **Elements: Rain, Insects, Crowd Murmurs, Traffic.**\n    *   **Spatial Feel: Echo in an Open Hall (Reverb), Small Room Acoustics.**\n\n*   **Pure Music**: **Instrument Type + Music Genre** + Emotion\n    *   **Structure: Piano Performance + Jazz + Melancholy.**\n    *   **Genres: Classical, Rock, Electronic.**\n\n**Tip**: It is recommended to use quotation marks \" \" to clarify sound content when writing prompts.\n"
          ],
          "color": "#222",
          "bgcolor": "#000"
      },
      {
          "id": 8,
          "type": "KlingTextToVideoWithAudio",
          "pos": [
              -1340,
              860
          ],
          "size": [
              500,
              430
          ],
          "flags": [],
          "order": 1,
          "mode": 0,
          "inputs": [],
          "outputs": [
              {
                  "name": "VIDEO",
                  "type": "VIDEO",
                  "links": [
                      5
                  ]
              }
          ],
          "properties": {
              "Node name for S&R": "KlingTextToVideoWithAudio"
          },
          "widgets_values": [
              "kling-v2-6",
              "Visual: In a livehouse, bathed in blue light, a high barstool is placed in the center, with the audience hidden in the shadows. \n\nDialog: [Short-haired female singer] sits on the high barstool, holding a wooden guitar, her fingers gently strumming the strings.\n\n[Short-haired female singer, heartfelt voice] sings: \"And I will try to fix you, all night long...\" When she reaches the chorus, [Short-haired female singer] looks out toward the audience. Background: The sound of clinking glasses. The camera switches between focusing on the short-haired female singer's fingers on the strings and her facial expression.",
              "pro",
              "16:9",
              10,
              true
          ],
          "color": "#432",
          "bgcolor": "#653"
      }
  ],
  "links": [
      [
          5,
          8,
          0,
          10,
          0,
          "VIDEO"
      ]
  ],
  "groups": [],
  "config": [],
  "extra": {
      "workflowRendererVersion": "LG",
      "ds": {
          "scale": 0.7385926294872244,
          "offset": [
              2137.1947320926997,
              -526.4337524397469
          ]
      },
      "frontendVersion": "1.35.7",
      "VHS_latentpreview": false,
      "VHS_latentpreviewrate": 0,
      "VHS_MetadataImage": true,
      "VHS_KeepIntermediate": true
  },
  "version": 0.4
127}

Kling2.6：文生视频（音画同步）

节点构成

官方标注的模型

工作流 JSON 复制

工作流 JSON