Generate AI Videos From Text or Images with Sora 2

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 →

{
  "meta": {
    "templateCredsSetupCompleted": true
  },
  "nodes": [
    {
      "id": "a85d1e91-bf05-4a5a-9759-15de2b1b50e8",
      "name": "Note: Mode Router",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        5280,
        2640
      ],
      "parameters": {
        "color": 3,
        "width": 332,
        "height": 192,
        "content": "## \ud83d\udd00 Input Mode Router\n\n**Purpose:** Branches to image-to-video if file uploaded, else text-to-video with refinement.\n\n**Note:** Switch checks filename; ensures GPT-5 processes text prompts."
      },
      "typeVersion": 1
    },
    {
      "id": "eda124e2-e1aa-4064-96a7-c31cbde19521",
      "name": "Note: Image Upload",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        5744,
        2080
      ],
      "parameters": {
        "color": 6,
        "width": 332,
        "height": 192,
        "content": "## \ud83d\uddbc\ufe0f Temp Image Upload\n\n**Purpose:** Uploads reference image to tmpfiles.org for Sora image-to-video.\n\n**Note:** Multipart POST; swaps URL to /dl/ for direct API access."
      },
      "typeVersion": 1
    },
    {
      "id": "1c76b2c1-9778-4f10-a078-6ce8eba97641",
      "name": "Note: Prompt Refiner",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        5488,
        2928
      ],
      "parameters": {
        "color": 5,
        "width": 332,
        "height": 192,
        "content": "## \ud83e\udd16 Prompt Refiner\n\n**Purpose:** Uses GPT-5 to enhance text prompts for Sora 2 text-to-video mode.\n\n**Note:** Mandatory for text branch; outputs JSON with refined prompt, ratio, duration."
      },
      "typeVersion": 1
    },
    {
      "id": "707ea9aa-81eb-47d1-b000-eb3238c70b94",
      "name": "Note: JSON Parser",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        5920,
        2944
      ],
      "parameters": {
        "color": 3,
        "width": 332,
        "height": 192,
        "content": "## \ud83d\udd0d JSON Output Parser\n\n**Purpose:** Validates GPT-5 response against schema for clean API params.\n\n**Note:** Ensures prompt (50-4000 chars), ratio (16:9/9:16), duration (4/8/12)."
      },
      "typeVersion": 1
    },
    {
      "id": "c474d947-6610-4731-bc3b-af7c09f926be",
      "name": "Note: Text-to-Video",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        6288,
        2752
      ],
      "parameters": {
        "color": 5,
        "width": 332,
        "height": 192,
        "content": "## \ud83c\udfa5 Text-to-Video Call\n\n**Purpose:** Submits refined prompt to fal.ai Sora 2 text endpoint (pro if selected).\n\n**Note:** Uses 720p res; calls /text-to-video or /pro; returns request_id for polling."
      },
      "typeVersion": 1
    },
    {
      "id": "607e987b-df5f-4d7a-8d49-b79440c62962",
      "name": "Note: Image-to-Video",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        6240,
        2144
      ],
      "parameters": {
        "color": 5,
        "width": 332,
        "height": 192,
        "content": "## \ud83d\uddbc\ufe0f Image-to-Video Call\n\n**Purpose:** Sends raw prompt + image URL to fal.ai Sora 2 image endpoint.\n\n**Note:** Auto res; calls /image-to-video or /pro; uses form ratio/duration directly."
      },
      "typeVersion": 1
    },
    {
      "id": "f50b63a0-dee7-4783-bcff-8b5d5b75949b",
      "name": "Video Input Form",
      "type": "n8n-nodes-base.formTrigger",
      "position": [
        5392,
        2448
      ],
      "parameters": {
        "options": {
          "appendAttribution": false
        },
        "formTitle": "Create a Video using Sora 2",
        "formFields": {
          "values": [
            {
              "fieldLabel": "Prompt",
              "requiredField": true
            },
            {
              "fieldType": "dropdown",
              "fieldLabel": "Aspect Ratio",
              "fieldOptions": {
                "values": [
                  {
                    "option": "9:16 (vertical)"
                  },
                  {
                    "option": "16:9 (Horizontal)"
                  }
                ]
              },
              "requiredField": true
            },
            {
              "fieldType": "checkbox",
              "fieldLabel": "Model",
              "fieldOptions": {
                "values": [
                  {
                    "option": "sora-2"
                  },
                  {
                    "option": "sora-2-pro"
                  }
                ]
              },
              "requiredField": true,
              "limitSelection": "exact"
            },
            {
              "fieldType": "checkbox",
              "fieldLabel": "Lenght",
              "fieldOptions": {
                "values": [
                  {
                    "option": "4s"
                  },
                  {
                    "option": "8s"
                  },
                  {
                    "option": "12s"
                  }
                ]
              },
              "requiredField": true,
              "limitSelection": "exact"
            },
            {
              "fieldType": "file",
              "fieldLabel": "Image",
              "multipleFiles": false,
              "acceptFileTypes": ".jpg,.jpeg,.png"
            }
          ]
        }
      },
      "typeVersion": 2.3
    },
    {
      "id": "0c7ab4d0-5a34-41c1-9ea8-5a145056cee6",
      "name": "Prompt Refiner",
      "type": "@n8n/n8n-nodes-langchain.chainLlm",
      "position": [
        5840,
        2592
      ],
      "parameters": {
        "text": "=User Query: {{ $json.Prompt }}\n\nApect Ratio: {{ $json['Aspect Ratio'] }}\n\nLenght: {{ $json.Lenght[0] }}",
        "batching": {},
        "messages": {
          "messageValues": [
            {
              "message": "=You are an expert AI video prompt engineer specializing in OpenAI's Sora 2 video generation model. Your role is to transform user input into professionally structured, cinematic prompts optimized for high-quality video generation.\n\n## Core Principles\n\n1. **Brevity for Reliability**: Shorter clips (4s) follow instructions more reliably than longer ones. Recommend 4s duration unless user specifically needs longer content.\n\n2. **Specificity Over Vagueness**: Replace abstract concepts with concrete, visual details. Transform \"beautiful street\" into \"wet asphalt, zebra crosswalk, neon signs reflecting in puddles.\"\n\n3. **One Beat Per Shot**: Each shot should contain ONE clear camera movement and ONE clear subject action. Avoid cramming multiple complex actions into a single clip.\n\n4. **Cinematic Thinking**: Treat prompts as storyboard descriptions or cinematographer briefs, not casual requests.\n\n## Prompt Structure Framework\n\nOrganize enhanced prompts using this hierarchy:\n\n### 1. Style & Format (Optional but Powerful)\n- Establish overall aesthetic early: \"1970s film,\" \"IMAX aerial,\" \"handheld documentary\"\n- Film stock references: \"35mm film,\" \"16mm with grain,\" \"digital capture\"\n- Color treatment: \"Kodak warm grade,\" \"teal and orange palette,\" \"desaturated noir\"\n\n### 2. Scene Description\n- Setting and environment with specific visual details\n- Character descriptions (clothing, age, demeanor)\n- Atmospheric elements (weather, time of day, lighting quality)\n- Props and set dressing that matter to the shot\n\n### 3. Cinematography\n**Camera shot**: Specify framing and angle\n- Examples: \"wide establishing shot, eye level,\" \"medium close-up, slight low angle,\" \"aerial wide shot, downward tilt\"\n\n**Lens/DOF**: When detail matters\n- Examples: \"35mm lens, shallow depth of field,\" \"50mm with background softness,\" \"wide angle for environmental context\"\n\n**Camera movement**: Keep it simple and precise\n- Examples: \"slow push-in,\" \"dolly left to right,\" \"static handheld,\" \"crane up revealing skyline\"\n\n**Mood**: Emotional tone\n- Examples: \"tense and cinematic,\" \"warm and nostalgic,\" \"playful suspense\"\n\n### 4. Lighting & Palette\nDescribe light quality and color anchors:\n- Light quality: \"soft window light,\" \"hard single source,\" \"diffused overhead\"\n- Direction: \"from camera left,\" \"backlit,\" \"rim lighting\"\n- Color anchors: Name 3-5 specific colors for palette consistency\n- Examples: \"warm key from overhead, cool rim from window; palette: amber, cream, teal\"\n\n### 5. Actions (Time-Based Beats)\nBreak down motion into countable beats:\n- Use specific verbs and counts: \"takes four steps,\" \"pauses for two seconds,\" \"turns and catches\"\n- Avoid: \"walks around\" \u2192 Use: \"takes three steps forward, pauses, looks left\"\n- Keep actions achievable within the duration\n\n### 6. Dialogue (If Applicable)\nFormat dialogue clearly:\n- Place in dedicated block with speaker labels\n- Keep lines short and natural (4s = 1-2 exchanges, 8s = 3-4 exchanges)\n- Example format:\n  ```\n  Dialogue:\n  - Character A: \"Short, natural line.\"\n  - Character B: \"Response that fits timing.\"\n  ```\n\n### 7. Audio/Sound (Optional)\nSuggest diegetic sounds to establish rhythm:\n- Examples: \"distant traffic hum,\" \"coffee machine hiss,\" \"paper rustle\"\n- Note: This is for pacing cues, not full soundtracks\n\n## Enhancement Guidelines\n\n### What to ADD:\n- Concrete visual details (colors, textures, specific objects)\n- Professional cinematography terms (shot types, camera movements)\n- Lighting direction and quality\n- Precise action beats with timing\n- Style references that set aesthetic tone\n- Specific color palette (3-5 colors)\n\n### What to REPLACE:\n- \"Beautiful\" \u2192 Specific visual qualities\n- \"Moves\" \u2192 Precise action with counts\n- \"Nice lighting\" \u2192 Light source, direction, quality\n- \"Cinematic\" \u2192 Actual film/lens specifications\n- \"Interesting angle\" \u2192 Specific shot type and framing\n\n### What to AVOID:\n- Multiple complex actions in one shot\n- Vague descriptors without visual specifics\n- Requesting duration/resolution in prose (these are API parameters)\n- Overcrowding shots with too many elements\n- Abstract emotions without visual manifestations\n\n## Duration Recommendations\n\nBased on user intent:\n- **4 seconds**: Default recommendation. Most reliable for instruction following. Best for single clear action.\n- **8 seconds**: When user needs slightly more development. Warn that this may be less reliable; suggest stitching two 4s clips instead.\n- **12 seconds**: Only when explicitly requested. Strongly recommend breaking into multiple 4s shots for better control.\n\n## Aspect Ratio Selection\n\n- **16:9**: Landscape, traditional video, cinematic scenes, wide vistas, desktop viewing\n- **9:16**: Portrait, social media (TikTok, Instagram Stories, Reels), mobile-first content, vertical stories\n\n## Transformation Process\n\n1. **Analyze** user input for core intent\n2. **Identify** missing cinematic elements (camera, lighting, specific actions)\n3. **Expand** vague descriptions into concrete visuals\n4. **Structure** using the framework above\n5. **Optimize** for the chosen duration\n6. **Balance** detail with creative freedom based on user needs\n\n## Examples of Weak \u2192 Strong Transformations\n\n**Weak**: \"A person walking down a street at night\"\n**Strong**: \"Style: Handheld 35mm with natural grain. A woman in a red coat takes five measured steps down a wet cobblestone street. Amber streetlights create pools of warm light; cool shadows between them. Camera: medium tracking shot, following from behind at shoulder level. Mood: solitary, urban noir. Lighting: practical streetlights only; reflections in puddles.\"\n\n**Weak**: \"Make it look cinematic\"\n**Strong**: \"Camera: wide shot, slow dolly-in. Lens: 40mm spherical with shallow DOF. Lighting: golden hour natural key from camera left, edge light on subject. Palette: warm amber, deep teal, cream. Mood: nostalgic, intimate.\"\n\n## Response Format\n\nAlways output your enhanced prompt as a JSON object with exactly three fields:\n- \"prompt\": The fully enhanced, professionally structured prompt (50-4000 characters)\n- \"aspect_ratio\": Either \"16:9\" or \"9:16\"\n- \"duration\": Either 4, 8, or 12 (integer, in seconds)\n\nAim for 60-150 words for standard prompts, more for complex cinematic shots requiring detailed specifications. Include professional cinematographic language while maintaining clarity."
            }
          ]
        },
        "promptType": "define",
        "hasOutputParser": true
      },
      "typeVersion": 1.7
    },
    {
      "id": "2cfdf665-263a-441a-abef-07136a766458",
      "name": "JSON Output Parser",
      "type": "@n8n/n8n-nodes-langchain.outputParserStructured",
      "position": [
        5984,
        2768
      ],
      "parameters": {
        "schemaType": "manual",
        "inputSchema": "{\n  \"$schema\": \"http://json-schema.org/draft-07/schema#\",\n  \"title\": \"Sora2VideoGenerationRequest\",\n  \"description\": \"Simplified schema for Sora 2 video generation with enhanced prompts\",\n  \"type\": \"object\",\n  \"required\": [\"prompt\", \"aspect_ratio\", \"duration\"],\n  \"properties\": {\n    \"prompt\": {\n      \"type\": \"string\",\n      \"description\": \"The fully enhanced, professionally structured prompt optimized for Sora 2 video generation with cinematography details, specific actions, lighting, and visual specifics\",\n      \"minLength\": 50,\n      \"maxLength\": 4000\n    },\n    \"aspect_ratio\": {\n      \"type\": \"string\",\n      \"enum\": [\"16:9\", \"9:16\"],\n      \"description\": \"Video aspect ratio. 16:9 for landscape/cinematic, 9:16 for portrait/social media\"\n    },\n    \"duration\": {\n      \"type\": \"integer\",\n      \"enum\": [4, 8, 12],\n      \"description\": \"Video duration in seconds. 4s is most reliable, 8s and 12s may have reduced instruction-following accuracy\"\n    }\n  }\n}"
      },
      "typeVersion": 1.3
    },
    {
      "id": "e857b653-7894-43d8-8598-8d6998076a65",
      "name": "Temp Image Upload",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        5888,
        2320
      ],
      "parameters": {
        "url": "=https://tmpfiles.org/api/v1/upload",
        "method": "POST",
        "options": {},
        "sendBody": true,
        "contentType": "multipart-form-data",
        "bodyParameters": {
          "parameters": [
            {
              "name": "file",
              "parameterType": "formBinaryData",
              "inputDataFieldName": "Image"
            }
          ]
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "e8760386-b433-473d-9099-bb2f03c7c3aa",
      "name": "Text-to-Video Call",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        6144,
        2592
      ],
      "parameters": {
        "url": "=https://queue.fal.run/fal-ai/sora-2/text-to-video{{ $('Video Input Form').item.json.Model[0] === 'sora-2-pro' ? '/pro' : '' }}",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"prompt\": \"{{ JSON.stringify($('Prompt Refiner').item.json.output.prompt.replaceAll(/\\\\n/g, '')).slice(1, -1) }}\",\n  \"resolution\": \"720p\",\n  \"aspect_ratio\": \"{{ $('Prompt Refiner').item.json.output.aspect_ratio }}\",\n  \"duration\": {{ $('Prompt Refiner').item.json.output.duration }}\n}",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "2d84b59f-4c4e-4fac-968a-81eb6482c04e",
      "name": "Input Mode Router",
      "type": "n8n-nodes-base.switch",
      "position": [
        5600,
        2448
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "outputKey": "Image to Video",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "dfdd231a-d2f6-4973-a068-ac13f2bbd506",
                    "operator": {
                      "type": "string",
                      "operation": "notEmpty",
                      "singleValue": true
                    },
                    "leftValue": "={{ $json.Image.filename }}",
                    "rightValue": ""
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "Text to Video ",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "68ac0648-f33e-4394-805d-a8a9b788f1df",
                    "operator": {
                      "type": "string",
                      "operation": "empty",
                      "singleValue": true
                    },
                    "leftValue": "={{ $json.Image.filename }}",
                    "rightValue": ""
                  }
                ]
              },
              "renameOutput": true
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.3
    },
    {
      "id": "eef5e174-4d2a-450f-8bac-dd343865ad6b",
      "name": "Image-to-Video Call",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        6064,
        2320
      ],
      "parameters": {
        "url": "=https://queue.fal.run/fal-ai/sora-2/image-to-video{{ $('Video Input Form').item.json.Model[0] === 'sora-2-pro' ? '/pro' : '' }}",
        "method": "POST",
        "options": {},
        "jsonBody": "={\n  \"prompt\": \"{{ JSON.stringify($('Video Input Form').item.json.Prompt.replaceAll(/\\\\n/g, '')).slice(1, -1) }}\",\n  \"resolution\": \"auto\",\n  \"aspect_ratio\": \"{{ $('Video Input Form').item.json['Aspect Ratio'].replaceAll(' (vertical)', '').replaceAll(' (Horizontal)', '') }}\",\n  \"duration\": {{ $('Video Input Form').item.json.Lenght[0].replaceAll('s', '') }},\n  \"image_url\": \"{{ $json.data.url.replaceAll('.org/', '.org/dl/') }}\"\n}",
        "sendBody": true,
        "specifyBody": "json",
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "c07d5074-c4b7-4f43-a0d7-f26e2cd37137",
      "name": "Wait 60 Seconds",
      "type": "n8n-nodes-base.wait",
      "position": [
        6336,
        2416
      ],
      "parameters": {
        "amount": 60
      },
      "typeVersion": 1.1
    },
    {
      "id": "557e1785-4e6c-4f2e-a9a4-3098b1d638cb",
      "name": "Status Check",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        6544,
        2416
      ],
      "parameters": {
        "url": "=https://queue.fal.run/fal-ai/sora-2/requests/{{ $json.request_id }}/status",
        "options": {},
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "320c2ee0-767d-4106-a605-b03bd1a80631",
      "name": "Status Router",
      "type": "n8n-nodes-base.switch",
      "position": [
        6752,
        2416
      ],
      "parameters": {
        "rules": {
          "values": [
            {
              "outputKey": "Done",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "d8b8dbdc-1ad9-4ab9-8b2d-e76fd5db0899",
                    "operator": {
                      "type": "string",
                      "operation": "equals"
                    },
                    "leftValue": "={{ $json.status }}",
                    "rightValue": "COMPLETED"
                  }
                ]
              },
              "renameOutput": true
            },
            {
              "outputKey": "Progress",
              "conditions": {
                "options": {
                  "version": 2,
                  "leftValue": "",
                  "caseSensitive": true,
                  "typeValidation": "strict"
                },
                "combinator": "and",
                "conditions": [
                  {
                    "id": "9c10982c-5f8c-4eec-9b8a-f4b42e99ecf9",
                    "operator": {
                      "type": "string",
                      "operation": "notEquals"
                    },
                    "leftValue": "={{ $json.status }}",
                    "rightValue": "COMPLETED"
                  }
                ]
              },
              "renameOutput": true
            }
          ]
        },
        "options": {}
      },
      "typeVersion": 3.2
    },
    {
      "id": "cfa44af4-e910-40cf-b581-1acee757871d",
      "name": "Retrieve Video",
      "type": "n8n-nodes-base.httpRequest",
      "position": [
        6944,
        2400
      ],
      "parameters": {
        "url": "=https://queue.fal.run/fal-ai/sora-2/requests/{{ $json.request_id }}",
        "options": {},
        "authentication": "genericCredentialType",
        "genericAuthType": "httpHeaderAuth"
      },
      "credentials": {
        "httpHeaderAuth": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 4.2
    },
    {
      "id": "6ce27f08-cae8-4a9b-bac3-2e01fa31c864",
      "name": "Video Redirect",
      "type": "n8n-nodes-base.form",
      "position": [
        7152,
        2400
      ],
      "parameters": {
        "options": {},
        "operation": "completion",
        "redirectUrl": "={{ $json.video.url }}",
        "respondWith": "redirect"
      },
      "typeVersion": 2.3
    },
    {
      "id": "d110e220-883b-4e3f-bbda-cd195ddf23dd",
      "name": "Overview Note8",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        4528,
        1984
      ],
      "parameters": {
        "color": 4,
        "width": 696,
        "height": 1184,
        "content": "# \ud83c\udfac Sora 2 Video Generator via Fal with GPT-5 Refinement\n\n## \ud83d\udccb What This Template Does\nGenerate videos using OpenAI's Sora 2 via fal.ai's four endpoints (text-to-video, text-to-video/pro, image-to-video, image-to-video/pro). Accepts form inputs for prompts, aspect ratios, models, durations (4-12s), and optional images. For text mode, GPT-5 refines prompts for cinematic quality; image mode uses raw input. Polls status asynchronously and redirects to the final video.\n\n## \ud83d\udd27 Prerequisites\n- n8n with HTTP Request and LangChain nodes\n- fal.ai account\n- OpenAI account (GPT-5 access)\n\n## \ud83d\udd11 Required Credentials\n\n### fal.ai API Setup\n1. fal.ai \u2192 Dashboard \u2192 API Keys\n2. Generate key with sora-2 permissions\n3. n8n: Header Auth (\"fal.ai\", Header: \"Authorization\", Value: \"Key [Your Key]\")\n\n### OpenAI API Setup\n1. platform.openai.com \u2192 API Keys \u2192 Create secret key\n2. n8n: OpenAI API credential (paste key, select GPT-5)\n\n## \u2699\ufe0f Configuration Steps\n1. Import JSON (Settings \u2192 Import)\n2. Assign creds to HTTP/LLM nodes\n3. Activate\u2014use form URL from trigger\n4. Test prompt; check executions\n5. Tune polling for longer clips\n\n## \ud83c\udfaf Use Cases\n- Social: 9:16 Reels from refined text (e.g., product anims)\n- Marketing: Image-to-8s promos (e.g., logo intros)\n- Education: 4s explainers (e.g., science demos)\n- Dev: Backend for app video gen\n\n## \u26a0\ufe0f Troubleshooting\n- Quota fail: Check fal.ai usage; upgrade/add waits\n- Refinement error: Verify GPT-5 schema output\n- Image reject: JPG/PNG <10MB; test tmpfiles\n- Poll timeout: Bump wait to 120s; add retry IF"
      },
      "typeVersion": 1
    },
    {
      "id": "6dad83d5-6cb1-4dca-90a1-c12048b5b544",
      "name": "Note: Form Trigger1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        5248,
        2176
      ],
      "parameters": {
        "color": 6,
        "width": 332,
        "height": 192,
        "content": "## \ud83d\udcdd Video Input Form\n\n**Purpose:** Captures user prompt, ratio, model, duration, and optional image via web form.\n\n**Note:** Required fields validated; activates webhook URL on workflow start."
      },
      "typeVersion": 1
    },
    {
      "id": "6e91faf7-a3c5-48ce-94d6-a993ea8e5d8e",
      "name": "Note: Polling Loop1",
      "type": "n8n-nodes-base.stickyNote",
      "position": [
        6688,
        2640
      ],
      "parameters": {
        "color": 2,
        "width": 332,
        "height": 192,
        "content": "## \u23f3 Status Polling Loop\n\n**Purpose:** Waits 60s, checks Sora status, loops until COMPLETED.\n\n**Note:** Switch routes to result or retry; handles all four endpoints uniformly."
      },
      "typeVersion": 1
    },
    {
      "id": "ad9eadd7-1e7f-4922-8ca7-6a673812ffd0",
      "name": "Refiner Model",
      "type": "@n8n/n8n-nodes-langchain.lmChatOpenAi",
      "position": [
        5840,
        2768
      ],
      "parameters": {
        "model": {
          "__rl": true,
          "mode": "list",
          "value": "gpt-5",
          "cachedResultName": "gpt-5"
        },
        "options": {}
      },
      "credentials": {
        "openAiApi": {
          "name": "<your credential>"
        }
      },
      "typeVersion": 1.2
    }
  ],
  "connections": {
    "Status Check": {
      "main": [
        [
          {
            "node": "Status Router",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Refiner Model": {
      "ai_languageModel": [
        [
          {
            "node": "Prompt Refiner",
            "type": "ai_languageModel",
            "index": 0
          }
        ]
      ]
    },
    "Status Router": {
      "main": [
        [
          {
            "node": "Retrieve Video",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Wait 60 Seconds",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Prompt Refiner": {
      "main": [
        [
          {
            "node": "Text-to-Video Call",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Retrieve Video": {
      "main": [
        [
          {
            "node": "Video Redirect",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Wait 60 Seconds": {
      "main": [
        [
          {
            "node": "Status Check",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Video Input Form": {
      "main": [
        [
          {
            "node": "Input Mode Router",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Input Mode Router": {
      "main": [
        [
          {
            "node": "Temp Image Upload",
            "type": "main",
            "index": 0
          }
        ],
        [
          {
            "node": "Prompt Refiner",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Temp Image Upload": {
      "main": [
        [
          {
            "node": "Image-to-Video Call",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "JSON Output Parser": {
      "ai_outputParser": [
        [
          {
            "node": "Prompt Refiner",
            "type": "ai_outputParser",
            "index": 0
          }
        ]
      ]
    },
    "Text-to-Video Call": {
      "main": [
        [
          {
            "node": "Wait 60 Seconds",
            "type": "main",
            "index": 0
          }
        ]
      ]
    },
    "Image-to-Video Call": {
      "main": [
        [
          {
            "node": "Wait 60 Seconds",
            "type": "main",
            "index": 0
          }
        ]
      ]
    }
  }
}

Credentials you'll need

Each integration node will prompt for credentials when you import. We strip credential IDs before publishing — you'll add your own.

• httpHeaderAuth
• openAiApi

About this workflow

Harness OpenAI's Sora 2 for instant video creation from text or images using fal.ai's API—powered by GPT-5 for refined prompts that ensure cinematic quality. This template processes form submissions, intelligently routes to text-to-video (with mandatory prompt enhancement) or…

Source: https://n8n.io/workflows/10139/ — original creator credit. Request a take-down →

More AI & RAG workflows → · Browse all categories →

Related workflows

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