{ "id": "ehdJCsJyErJC1jtK", "name": "7. Generate 3D Models & Textures from Images with Hunyuan3D AI", "tags": [], "nodes": [ { "id": "2f62f2a8-13d0-44d2-8b81-fedc9b2a703c", "name": "On clicking 'execute'", "type": "n8n-nodes-base.manualTrigger", "position": [ -272, -32 ], "parameters": {}, "typeVersion": 1 }, { "id": "733f09b8-cbcb-40d1-a453-f181eafe0b56", "name": "Set API Key", "type": "n8n-nodes-base.set", "position": [ -64, -32 ], "parameters": { "options": {}, "assignments": { "assignments": [ { "id": "64cd57c7-2224-48a6-88df-c37b310f8eb3", "name": "replicate_api_key", "type": "string", "value": "YOUR_REPLICATE_API_KEY" } ] } }, "typeVersion": 3.3 }, { "id": "84d49ec1-b81f-430f-977e-a246e70c7196", "name": "Create Prediction", "type": "n8n-nodes-base.httpRequest", "position": [ 176, -32 ], "parameters": { "url": "https://api.replicate.com/v1/predictions", "method": "POST", "options": { "timeout": 60000 }, "jsonBody": "{\n \"version\": \"70d0d816b74578a2ee5e7906284ab8bd26cf4f6a3fb7797dcd58059b803ae75f\",\n \"input\": {\n \"image\": \"https://example.com/input.other\",\n \"seed\": 1234,\n \"steps\": 50,\n \"num_chunks\": 8000,\n \"max_facenum\": 20000,\n \"guidance_scale\": 7.5,\n \"generate_texture\": true,\n \"remove_background\": true\n }\n}", "sendBody": true, "sendHeaders": true, "specifyBody": "json", "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Authorization", "value": "={{ 'Bearer ' + $('Set API Key').item.json.replicate_api_key }}" }, { "name": "Content-Type", "value": "application/json" } ] } }, "typeVersion": 4.2 }, { "id": "db470338-596d-4b1e-b34a-d6559ee22fec", "name": "Extract Prediction ID", "type": "n8n-nodes-base.code", "position": [ 384, -32 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "// Extract prediction ID and initial status\\nconst prediction = $input.item.json;\\nconst predictionId = prediction.id;\\nconst initialStatus = prediction.status;\\n\\n// Store the prediction ID for polling\\nreturn {\\n predictionId: predictionId,\\n status: initialStatus,\\n predictionUrl: `https://api.replicate.com/v1/predictions/${predictionId}`\\n};" }, "typeVersion": 2 }, { "id": "a92796bf-b794-4c3e-a277-00319cd5dc33", "name": "Wait", "type": "n8n-nodes-base.wait", "position": [ 608, -32 ], "parameters": { "unit": "seconds", "amount": 2 }, "typeVersion": 1 }, { "id": "05d9be59-6e59-4326-b897-c658e6cb5311", "name": "Check Prediction Status", "type": "n8n-nodes-base.httpRequest", "position": [ 832, -32 ], "parameters": { "url": "={{ $json.predictionUrl }}", "options": {}, "sendHeaders": true, "authentication": "genericCredentialType", "genericAuthType": "httpHeaderAuth", "headerParameters": { "parameters": [ { "name": "Authorization", "value": "={{ 'Bearer ' + $('Set API Key').item.json.replicate_api_key }}" } ] } }, "typeVersion": 4.2 }, { "id": "0e8f8825-9556-4d68-b2ee-b7c71922b8f2", "name": "Check If Complete", "type": "n8n-nodes-base.if", "position": [ 1056, -32 ], "parameters": { "conditions": { "boolean": [ { "value1": "={{ $json.status }}", "value2": "succeeded" } ] } }, "typeVersion": 1 }, { "id": "91e21baf-7044-42f0-a899-49aca23f730d", "name": "Process Result", "type": "n8n-nodes-base.code", "position": [ 1296, -144 ], "parameters": { "mode": "runOnceForEachItem", "jsCode": "// Process the completed prediction\\nconst result = $input.item.json;\\n\\nreturn {\\n status: result.status,\\n output: result.output,\\n metrics: result.metrics,\\n created_at: result.created_at,\\n completed_at: result.completed_at,\\n model: 'ndreca/hunyuan3d-2.1-test',\\n other_url: result.output\\n};" }, "typeVersion": 2 }, { "id": "2a4b07d5-0691-48e8-8247-84f604db01ca", "name": "Sticky Note", "type": "n8n-nodes-base.stickyNote", "position": [ -336, -912 ], "parameters": { "color": 2, "width": 438, "height": 1087, "content": "## \u26a1 **Section 1: Trigger & Setup**\n\n### \u2699\ufe0f **Nodes**\n\n1\ufe0f\u20e3 **On Clicking \u201cExecute\u201d**\n\n* **What it does:** Starts the workflow manually in n8n.\n* **Why it\u2019s useful:** Great for testing or one-off runs before automation.\n\n2\ufe0f\u20e3 **Set API Key**\n\n* **What it does:** Stores your **Replicate API Key**.\n* **Why it\u2019s useful:** Keeps authentication secure and reusable across HTTP nodes.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* No coding needed \u2014 just paste your API key once.\n* Easy to test: press **Execute**, and you\u2019re live.\n\n---\n\n" }, "typeVersion": 1 }, { "id": "f6f876d7-0419-4f67-97b9-eb343c390afb", "name": "Sticky Note9", "type": "n8n-nodes-base.stickyNote", "position": [ -2112, -576 ], "parameters": { "color": 4, "width": 1300, "height": 320, "content": "=======================================\n WORKFLOW ASSISTANCE\n=======================================\nFor any questions or support, please contact:\n Yaron@nofluff.online\n\nExplore more tips and tutorials here:\n - YouTube: https://www.youtube.com/@YaronBeen/videos\n - LinkedIn: https://www.linkedin.com/in/yaronbeen/\n=======================================\n" }, "typeVersion": 1 }, { "id": "dbd692e5-b0d5-4652-adc6-893eeb6d2882", "name": "Sticky Note4", "type": "n8n-nodes-base.stickyNote", "position": [ -2112, -240 ], "parameters": { "color": 4, "width": 1289, "height": 4094, "content": "# Generate 3D Models & Textures from Images with Hunyuan3D AI\n\nThis workflow connects **n8n \u2192 Replicate API** to generate 3D-like outputs using the **ndreca/hunyuan3d-2.1-test** model. It handles everything: sending the request, waiting for processing, checking status, and returning results.\n\n---\n\n## \u26a1 **Section 1: Trigger & Setup**\n\n### \u2699\ufe0f **Nodes**\n\n1\ufe0f\u20e3 **On Clicking \u201cExecute\u201d**\n\n* **What it does:** Starts the workflow manually in n8n.\n* **Why it\u2019s useful:** Great for testing or one-off runs before automation.\n\n2\ufe0f\u20e3 **Set API Key**\n\n* **What it does:** Stores your **Replicate API Key**.\n* **Why it\u2019s useful:** Keeps authentication secure and reusable across HTTP nodes.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* No coding needed \u2014 just paste your API key once.\n* Easy to test: press **Execute**, and you\u2019re live.\n\n---\n\n## \ud83e\udd16 **Section 2: Send Job to Replicate**\n\n### \u2699\ufe0f **Nodes**\n\n3\ufe0f\u20e3 **Create Prediction (HTTP Request)**\n\n* **What it does:** Sends a **POST request** to Replicate\u2019s API with:\n\n * Model version (`70d0d816...ae75f`)\n * Input image URL\n * Parameters like `steps`, `seed`, `generate_texture`, `remove_background`\n* **Why it\u2019s useful:** This kicks off the AI generation job on Replicate\u2019s servers.\n\n4\ufe0f\u20e3 **Extract Prediction ID (Code)**\n\n* **What it does:** Grabs the **prediction ID** from the API response and builds a status-check URL.\n* **Why it\u2019s useful:** Every job has a unique ID \u2014 this lets us track progress later.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* You don\u2019t need to worry about JSON parsing \u2014 the workflow extracts the ID automatically.\n* Everything is reusable if you run multiple generations.\n\n---\n\n## \u23f3 **Section 3: Poll Until Complete**\n\n### \u2699\ufe0f **Nodes**\n\n5\ufe0f\u20e3 **Wait (2s)**\n\n* **What it does:** Pauses for 2 seconds before checking the job status.\n* **Why it\u2019s useful:** Prevents spamming the API with too many requests.\n\n6\ufe0f\u20e3 **Check Prediction Status (HTTP Request)**\n\n* **What it does:** GET request to see if the job is finished.\n\n7\ufe0f\u20e3 **Check If Complete (IF Node)**\n\n* **What it does:**\n\n * If `status = succeeded` \u2192 process results.\n * If not \u2192 loops back to **Wait** and checks again.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* Handles waiting logic for you \u2014 no manual refreshing needed.\n* Keeps looping until the AI job is really done.\n\n---\n\n## \ud83d\udce6 **Section 4: Process the Result**\n\n### \u2699\ufe0f **Nodes**\n\n8\ufe0f\u20e3 **Process Result (Code)**\n\n* **What it does:** Extracts:\n\n * `status`\n * `output` (final generated file/URL)\n * `metrics` (performance stats)\n * Timestamps (`created_at`, `completed_at`)\n * Model info\n* **Why it\u2019s useful:** Packages the response neatly for storage, email, or sending elsewhere.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* Get clean, structured data ready for saving or sending.\n* Can be extended easily: push output to **Google Drive, Notion, or Slack**.\n\n---\n\n## \ud83d\udcca **Workflow Overview**\n\n| Section | What happens | Key Nodes | Benefit |\n| --------------------- | --------------------------------- | ----------------------------- | --------------------------------- |\n| \u26a1 Trigger & Setup | Start workflow + set API key | Manual Trigger, Set | Easy one-click start |\n| \ud83e\udd16 Send Job | Send input & get prediction ID | Create Prediction, Extract ID | Launches AI generation |\n| \u23f3 Poll Until Complete | Waits + checks status until ready | Wait, Check Status, IF | Automated loop, no manual refresh |\n| \ud83d\udce6 Process Result | Collects output & metrics | Process Result | Clean result for next steps |\n\n---\n\n## \ud83c\udfaf **Overall Benefits**\n\n\u2705 Fully automates Replicate model runs\n\u2705 Handles waiting, retries, and completion checks\n\u2705 Clean final output with status + metrics\n\u2705 Beginner-friendly \u2014 just add API key + input image\n\u2705 Extensible: connect results to Google Sheets, Gmail, Slack, or databases\n\n---\n\n\u2728 In short: This is a **no-code AI image-to-3D content generator** powered by **Replicate** and automated by **n8n**.\n\n---\n" }, "typeVersion": 1 }, { "id": "f6237bb8-0a60-4774-86fa-9dcde7311164", "name": "Sticky Note1", "type": "n8n-nodes-base.stickyNote", "position": [ 128, -1088 ], "parameters": { "color": 5, "width": 406, "height": 1263, "content": "## \ud83e\udd16 **Section 2: Send Job to Replicate**\n\n### \u2699\ufe0f **Nodes**\n\n3\ufe0f\u20e3 **Create Prediction (HTTP Request)**\n\n* **What it does:** Sends a **POST request** to Replicate\u2019s API with:\n\n * Model version (`70d0d816...ae75f`)\n * Input image URL\n * Parameters like `steps`, `seed`, `generate_texture`, `remove_background`\n* **Why it\u2019s useful:** This kicks off the AI generation job on Replicate\u2019s servers.\n\n4\ufe0f\u20e3 **Extract Prediction ID (Code)**\n\n* **What it does:** Grabs the **prediction ID** from the API response and builds a status-check URL.\n* **Why it\u2019s useful:** Every job has a unique ID \u2014 this lets us track progress later.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* You don\u2019t need to worry about JSON parsing \u2014 the workflow extracts the ID automatically.\n* Everything is reusable if you run multiple generations.\n\n---\n\n" }, "typeVersion": 1 }, { "id": "ad7e485f-02c1-4716-a59d-d8624fef1473", "name": "Sticky Note2", "type": "n8n-nodes-base.stickyNote", "position": [ 560, -1024 ], "parameters": { "color": 6, "width": 614, "height": 1199, "content": "## \u23f3 **Section 3: Poll Until Complete**\n\n### \u2699\ufe0f **Nodes**\n\n5\ufe0f\u20e3 **Wait (2s)**\n* **What it does:** Pauses for 2 seconds before checking the job status.\n* **Why it\u2019s useful:** Prevents spamming the API with too many requests.\n\n6\ufe0f\u20e3 **Check Prediction Status (HTTP Request)**\n\n* **What it does:** GET request to see if the job is finished.\n\n7\ufe0f\u20e3 **Check If Complete (IF Node)**\n\n* **What it does:**\n\n * If `status = succeeded` \u2192 process results.\n * If not \u2192 loops back to **Wait** and checks again.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* Handles waiting logic for you \u2014 no manual refreshing needed.\n* Keeps looping until the AI job is really done.\n\n---\n\n" }, "typeVersion": 1 }, { "id": "a34db2ed-539b-461f-99e3-8f5fdef3e750", "name": "Sticky Note3", "type": "n8n-nodes-base.stickyNote", "position": [ 1200, -928 ], "parameters": { "color": 3, "width": 310, "height": 1103, "content": "## \ud83d\udce6 **Section 4: Process the Result**\n\n### \u2699\ufe0f **Nodes**\n\n8\ufe0f\u20e3 **Process Result (Code)**\n\n* **What it does:** Extracts:\n\n * `status`\n * `output` (final generated file/URL)\n * `metrics` (performance stats)\n * Timestamps (`created_at`, `completed_at`)\n * Model info\n* **Why it\u2019s useful:** Packages the response neatly for storage, email, or sending elsewhere.\n\n---\n\n\ud83d\udca1 **Beginner Benefit**\n\n* Get clean, structured data ready for saving or sending.\n* Can be extended easily: push output to **Google Drive, Notion, or Slack**.\n\n---\n\n" }, "typeVersion": 1 } ], "active": false, "settings": { "executionOrder": "v1" }, "versionId": "413b414a-ffc1-4e47-9272-4f1e1d136bd0", "connections": { "Wait": { "main": [ [ { "node": "Check Prediction Status", "type": "main", "index": 0 } ] ] }, "Set API Key": { "main": [ [ { "node": "Create Prediction", "type": "main", "index": 0 } ] ] }, "Check If Complete": { "main": [ [ { "node": "Process Result", "type": "main", "index": 0 } ], [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "Create Prediction": { "main": [ [ { "node": "Extract Prediction ID", "type": "main", "index": 0 } ] ] }, "Extract Prediction ID": { "main": [ [ { "node": "Wait", "type": "main", "index": 0 } ] ] }, "On clicking 'execute'": { "main": [ [ { "node": "Set API Key", "type": "main", "index": 0 } ] ] }, "Check Prediction Status": { "main": [ [ { "node": "Check If Complete", "type": "main", "index": 0 } ] ] } } }