工作流 / 视频 / Gemini Omni 1.1 Flash：视频编辑

Gemini Omni 1.1 Flash：视频编辑

Gemini Omni 1.1 Flash: Video Edit

通过自然语言对话与Gemini Omni 1.1 Flash编辑视频。上传一个片段（10秒或更短）并描述更改：交换背景、重新设计场景、添加或移除元素，模型会在保留所有未提及内容的同时应用编辑。添加"保持其他所有内容不变"以获得最大一致性；简单提示效果最佳。输出带有原始音频的视频，比例为16:9或9:16，支持1080p/4K输出。非常适合混音、风格更改和迭代优化，无需从头重新生成。

视频 4 个节点 1 个输入 210 次使用 ComfyUI ≥ 0.34.2 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

GeminiVideoOmniV2 × 1

SaveVideo × 1

MarkdownNote × 1

LoadVideo × 1

官方标注的模型

Gemini Omni 1.1 Flash

工作流 JSON

和上面「下载工作流 JSON」是同一份文件。

1{
  "id": "7e83a61c-87e6-43db-b836-8a684bbc8993",
  "revision": 0,
  "last_node_id": 14,
  "last_link_id": 15,
  "nodes": [
      {
          "id": 7,
          "type": "GeminiVideoOmniV2",
          "pos": [
              446,
              1120
          ],
          "size": [
              400,
              369.875
          ],
          "flags": [],
          "order": 2,
          "mode": 0,
          "inputs": [
              {
                  "label": "image_1",
                  "name": "model.images.image_1",
                  "shape": 7,
                  "type": "IMAGE",
                  "link": null
              },
              {
                  "label": "video_1",
                  "name": "model.videos.video_1",
                  "shape": 7,
                  "type": "VIDEO",
                  "link": 15
              },
              {
                  "label": "video_2",
                  "name": "model.videos.video_2",
                  "shape": 7,
                  "type": "VIDEO",
                  "link": null
              }
          ],
          "outputs": [
              {
                  "name": "VIDEO",
                  "type": "VIDEO",
                  "links": [
                      7
                  ]
              },
              {
                  "name": "STRING",
                  "type": "STRING",
                  "links": null
              }
          ],
          "properties": {
              "Node name for S&R": "GeminiVideoOmniV2"
          },
          "widgets_values": [
              "Omni Flash 1.1",
              "Change the character in the video to a walking human‑shaped cactus",
              "720p",
              "16:9",
              "edit",
              1228915018,
              "randomize",
              "randomize"
          ],
          "color": "#432",
          "bgcolor": "#653"
      },
      {
          "id": 8,
          "type": "SaveVideo",
          "pos": [
              894,
              1120
          ],
          "size": [
              390,
              381.890625
          ],
          "flags": [],
          "order": 3,
          "mode": 0,
          "inputs": [
              {
                  "name": "video",
                  "type": "VIDEO",
                  "link": 7
              }
          ],
          "outputs": [
              {
                  "name": "video",
                  "type": "VIDEO",
                  "links": null
              }
          ],
          "properties": [],
          "widgets_values": [
              "video/Omni_Flash_1.1_video_edit",
              "auto",
              "auto",
              "auto"
          ]
      },
      {
          "id": 12,
          "type": "MarkdownNote",
          "pos": [
              -340,
              1120
          ],
          "size": [
              360,
              380
          ],
          "flags": [],
          "order": 0,
          "mode": 0,
          "inputs": [],
          "outputs": [],
          "properties": [],
          "widgets_values": [
              "## Input Asset\n\n- [hooded_wanderer_planet_bridge.mp4](https://raw.githubusercontent.com/Comfy-Org/workflow_templates/refs/heads/main/input/hooded_wanderer_planet_bridge.mp4) — required workflow input (`input/hooded_wanderer_planet_bridge.mp4`)\n\n\n## Report Issue\n\nNote: Please update ComfyUI first ([guide](https://docs.comfy.org/installation/update_comfyui)) and prepare required models. Desktop/Cloud updates follow stable releases, so some nightly-supported models may not be available yet.\n\n- Cannot run / runtime errors: [ComfyUI/issues](https://github.com/comfyanonymous/ComfyUI/issues)\n- UI / frontend issues: [ComfyUI_frontend/issues](https://github.com/Comfy-Org/ComfyUI_frontend/issues)\n- Workflow issues: [workflow_templates/issues](https://github.com/Comfy-Org/workflow_templates/issues)\n"
          ],
          "color": "#222",
          "bgcolor": "#000"
      },
      {
          "id": 14,
          "type": "LoadVideo",
          "pos": [
              68,
              1120
          ],
          "size": [
              330,
              370
          ],
          "flags": [],
          "order": 1,
          "mode": 0,
          "inputs": [],
          "outputs": [
              {
                  "name": "VIDEO",
                  "type": "VIDEO",
                  "links": [
                      15
                  ]
              }
          ],
          "properties": {
              "Node name for S&R": "LoadVideo"
          },
          "widgets_values": [
              "hooded_wanderer_planet_bridge.mp4",
              "image"
          ]
      }
  ],
  "links": [
      [
          7,
          7,
          0,
          8,
          0,
          "VIDEO"
      ],
      [
          15,
          14,
          0,
          7,
          1,
          "VIDEO"
      ]
  ],
  "groups": [],
  "config": [],
  "extra": {
      "ds": {
          "scale": 0.7959911789204484,
          "offset": [
              481.9179202480506,
              -743.5683562620687
          ]
      },
      "frontendVersion": "1.48.7",
      "VHS_latentpreview": false,
      "VHS_latentpreviewrate": 0,
      "VHS_MetadataImage": true,
      "VHS_KeepIntermediate": true
  },
  "version": 0.4
201}

Gemini Omni 1.1 Flash：视频编辑

节点构成

官方标注的模型

工作流 JSON 复制

工作流 JSON