Replicate.com

🎯 Purpose

The ReplicateCom node connects your workflow to AI models hosted on Replicate.com, enabling capabilities such as image generation, text processing, audio synthesis, document analysis, and more.
It sends your workflow data to a selected model and returns the model’s output for downstream steps.

---

🤖 What This Node Does

This node sends data from your workflow to AI models on Replicate.com and returns the AI-generated results. You can use it to:

• Generate images from text descriptions
• Process and enhance existing images
• Convert text to speech
• Analyze documents and extract information
• Create music or sound effects
• Transform data using advanced AI models

---

📥 Inputs

• Dynamic data from prior nodes that will be passed to the chosen Replicate model.
• Specific inputs depend on the model and its parameters selected in the node.

---

📤 Outputs

• AI-generated results (text, URLs to files, structured data) from the selected model.
• Can be returned appended to original data or as result-only, based on Output Option.

Output Format (example):

 {
   "replicate_response": "AI-generated result here (text or URL)"
 }
 ```

---

## ⚙️ Parameters
| Name | Type | Required | Default | Description |
|------|------|----------|---------|-------------|
| **API Token (`apikey`)** | Password | ✅ | Empty | Replicate.com personal access token. |
| **Model URL (`modelApiUrl`)** | Text | ✅ | Empty | The web address of the specific model to use. |
| **Model Version (`modelVersion`)** | Text | Optional | Empty | Exact model version for consistent results. |
| **Browse Models** | Action button | Optional | — | Opens a searchable catalog of available models. |
| **Model Parameters (`modelParameters`)** | Visual editor | Optional | Empty | Configure model-specific inputs (shown after model selection). |
| **Download Output (`downloadOutput`)** | Toggle | Optional | Off | Automatically download generated files (images/audio/video). |
| **Download Column File Name (`downloadColumnFileName`)** | Text | Required if download enabled | Empty | Naming pattern for downloaded files. |
| **Download Directory (`downloadDirectory`)** | Smart text | Required if download enabled | Empty | Folder where downloaded files are saved. |
| **Output Option (`outTransformId`)** | Dropdown | ✅ | Original + appended result | Choose to append results or return only the result column. |
| **Result Property Name (`outColumnName`)** | Text | ✅ | `replicate_response` | Name of the property to store AI results. |

---

## 🔧 Step-by-Step Configuration
1. **Add Node & Connect:** Place the **ReplicateCom** node and connect it to your data source.
2. **Authenticate:** Enter your **API Token (`apikey`)** in **Authentication**.
3. **Choose Model:** In **Model**, set **Model URL** and optional **Model Version**, or use **Browse Models**.  You can visit Replicate's website to browse their model here: https://replicate.com/explore
4. **Set Parameters:** Configure **Model Parameters** shown for the selected model (e.g., size, style, prompt).
5. **(Optional) Downloads:** Toggle **Download Output** and specify **file name** and **directory**.
6. **Output Format:** Pick **Output Option** and set **Result Property Name**.
7. **Test:** Run a test to verify model output and (if enabled) file downloads.

---