Ltx 2.3 Dynamic Text-to-video

The workflow JSON

Copy or download the full n8n JSON below. Paste it into a new n8n workflow, add your credentials, activate. Full import guide →

{
  "name": "LTX 2.3 Dynamic Text-to-Video",
  "nodes": [
    {
      "parameters": {
        "content": "## LTX 2.3 Text-to-Video\n\nThis workflow finds the most available `ltx23-*` model first, then runs text-to-video.\n\n### Setup\n1. Install `n8n-nodes-sogni`\n2. Add Sogni credentials\n3. Click Test Workflow\n\n### Why dynamic selection?\n- LTX 2.3 model IDs can change as new presets land\n- This avoids hardcoding a specific model ID\n- Frames are set to an `8n+1` safe value for LTX",
        "height": 360,
        "width": 360,
        "color": 5
      },
      "type": "n8n-nodes-base.stickyNote",
      "typeVersion": 1,
      "position": [
        -120,
        80
      ],
      "id": "sticky-ltx23-t2v-info",
      "name": "LTX 2.3 T2V Info"
    },
    {
      "parameters": {},
      "id": "start-node",
      "name": "When clicking 'Test workflow'",
      "type": "n8n-nodes-base.manualTrigger",
      "typeVersion": 1,
      "position": [
        220,
        280
      ]
    },
    {
      "parameters": {
        "resource": "model",
        "operation": "getAll"
      },
      "id": "get-models",
      "name": "Get All Models",
      "type": "n8n-nodes-sogni.sogni",
      "typeVersion": 1,
      "position": [
        460,
        280
      ],
      "notes": "Fetches all currently available Sogni models"
    },
    {
      "parameters": {
        "jsCode": "const ltx23Models = $input.all()\n  .map((item) => item.json)\n  .filter((model) => {\n    const id = String(model.id || '').toLowerCase();\n    return id.startsWith('ltx23-') || id.startsWith('ltx2.3-');\n  })\n  .sort((a, b) => (b.workerCount || 0) - (a.workerCount || 0));\n\nif (ltx23Models.length === 0) {\n  throw new Error('No LTX 2.3 models are available right now. Try again later or open the video model dropdown to choose another family.');\n}\n\nconst bestModel = ltx23Models[0];\n\nreturn {\n  json: {\n    modelId: bestModel.id,\n    modelName: bestModel.name || bestModel.id,\n    workerCount: bestModel.workerCount || 0,\n    recommendedSteps: bestModel.recommendedSettings?.steps || 20,\n    recommendedGuidance: bestModel.recommendedSettings?.guidance || 3.5,\n    frames: 113,\n    fps: 24\n  }\n};"
      },
      "id": "select-ltx23-model",
      "name": "Select LTX 2.3 Model",
      "type": "n8n-nodes-base.code",
      "typeVersion": 2,
      "position": [
        700,
        280
      ],
      "notes": "Picks the LTX 2.3 model with the most workers"
    },
    {
      "parameters": {
        "resource": "video",
        "operation": "generate",
        "videoModelId": "={{ $json.modelId }}",
        "videoPositivePrompt": "A cinematic tracking shot through a rain-soaked cyberpunk market at night, volumetric lighting, reflective puddles, smooth camera motion",
        "videoNetwork": "fast",
        "videoAdditionalFields": {
          "videoSettings": {
            "negativePrompt": "blurry, noisy, warped faces, jitter, flicker",
            "numberOfMedia": 1,
            "frames": "={{ $json.frames }}",
            "duration": 5,
            "fps": "={{ $json.fps }}",
            "steps": "={{ $json.recommendedSteps }}",
            "guidance": "={{ $json.recommendedGuidance }}"
          },
          "output": {
            "downloadVideos": true,
            "outputFormat": "mp4",
            "width": 768,
            "height": 768
          },
          "advanced": {
            "tokenType": "spark",
            "timeout": 600000,
            "autoResizeVideoAssets": true
          }
        }
      },
      "id": "generate-ltx23-video",
      "name": "Generate LTX 2.3 Video",
      "type": "n8n-nodes-sogni.sogni",
      "typeVersion": 1,
      "position": [
        960,
        280
      ],
      "notes": "Uses the selected LTX 2.3 model for text-to-video generation"
    }
  ],
  "connections": {
    "When clicking 'Test workflow'": {
      "main": [
        [
          {
            "node": "Get All Models",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Get All Models": {
      "main": [
        [
          {
            "node": "Select LTX 2.3 Model",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Select LTX 2.3 Model": {
      "main": [
        [
          {
            "node": "Generate LTX 2.3 Video",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  },
  "settings": {
    "executionOrder": "v1"
  },
  "staticData": null,
  "tags": [],
  "triggerCount": 0,
  "meta": {
    "templateCredsSetupCompleted": false
  }
}

About this workflow

LTX 2.3 Dynamic Text-to-Video. Uses n8n-nodes-sogni. Event-driven trigger; 5 nodes.

Source: https://github.com/Sogni-AI/n8n-nodes-sogni/blob/7076f6b87ded4436b16ef4e077542b85fec77778/examples/11-ltx23-dynamic-text-to-video.json — original creator credit. Request a take-down →

More General workflows → · Browse all categories →

Related workflows

Workflows that share integrations, category, or trigger type with this one. All free to copy and import.