Upload Nodes
Upload nodes let you bring your own files into Armox workflows. Use your images as references, your videos as starting points, or your audio for voice cloning.
What Are Upload Nodes?
Upload nodes are your gateway for bringing external files into Armox:
- 📤 Upload files — Images, videos, or audio
- 🔗 Connect to AI — Use uploads as inputs for generation
- 🎨 Transform content — Edit, enhance, or animate your files
Adding an Upload Node
- Open the node sidebar on the left
- Find Upload in the list
- Drag it onto your canvas
Uploading Files
Method 1: Click to Browse
- Click the upload area in the node
- Browse your computer
- Select a file
Method 2: Drag and Drop
- Find the file on your computer
- Drag it directly onto the Upload node
- Drop to upload
Supported File Formats
Images
| Format | Extension |
|---|---|
| JPEG | .jpg, .jpeg |
| PNG | .png |
| WebP | .webp |
| GIF | .gif |
Videos
| Format | Extension |
|---|---|
| MP4 | .mp4 |
| MOV | .mov |
| WebM | .webm |
Audio
| Format | Extension |
|---|---|
| MP3 | .mp3 |
| WAV | .wav |
| M4A | .m4a |
Output Types
The Upload node's output type depends on what you upload:
| Upload Type | Output Color | Connects To |
|---|---|---|
| Image | Blue | Image nodes, Video nodes, Tool nodes |
| Video | Purple | Video nodes, Tool nodes |
| Audio | Orange | Audio nodes, Video nodes |
Common Use Cases
Reference Images for Style Transfer
Use your image to guide AI generation:
[Upload Node (Image)] → [Image Node (Flux Kontext)] Your photo → AI-edited version
Example: Upload a product photo, connect to Flux Kontext, prompt "place on beach background"
Image-to-Video Animation
Animate a still image:
[Upload Node (Image)] → [Video Node] Your image → Animated video
Example: Upload a portrait, connect to video node, prompt "person slowly turns head"
Voice Cloning Source
Provide a voice sample for cloning:
[Upload Node (Audio)] → [Audio Node (XTTS)] Voice sample → Cloned speech
Example: Upload 20 seconds of someone speaking, clone their voice
Image Enhancement
Improve your existing images:
[Upload Node (Image)] → [Tool Node (Upscaler)] Low-res image → High-res image
Background Removal
Remove backgrounds from your photos:
[Upload Node (Image)] → [Tool Node (BG Remover)] Photo with background → Transparent background
Best Practices for Uploads
Image Uploads
| Tip | Why |
|---|---|
| Use high-resolution images | Better AI results |
| Clear, well-lit subjects | Easier for AI to process |
| Simple compositions | More predictable results |
| Common formats (JPG, PNG) | Best compatibility |
Video Uploads
| Tip | Why |
|---|---|
| Short clips (under 30s) | Faster processing |
| Stable footage | Better for AI analysis |
| Good lighting | Clearer results |
| Standard formats (MP4) | Best compatibility |
Audio Uploads
| Tip | Why |
|---|---|
| Clear recordings | Better voice cloning |
| Single speaker | Avoids confusion |
| No background noise | Cleaner output |
| 10-30 seconds | Optimal for cloning |
File Size Limits
Keep your uploads within these limits:
| Type | Max Size |
|---|---|
| Images | 10 MB |
| Videos | 100 MB |
| Audio | 25 MB |
💡 Tip: Compress large files before uploading for faster processing.
Workflow Examples
Product Photo Enhancement
- Upload your product photo
- Connect to Background Remover tool
- Connect result to Image Node (Flux Kontext)
- Prompt: "Place product on elegant marble surface, studio lighting"
- Connect to Upscaler if needed
[Upload] → [BG Remover] → [Image Node] → [Upscaler]
Portrait Animation
- Upload a portrait photo
- Connect to Video Node
- Prompt: "Subject slowly smiles, slight head tilt, natural movement"
- Generate animated portrait
[Upload] → [Video Node]
Custom Voiceover
- Upload voice sample (your voice or talent)
- Connect to Voice Cloning node
- Add Text Node with script
- Generate voiceover in that voice
[Upload (Audio)] → [Voice Clone Node] ← [Text Node (Script)]
Troubleshooting
Upload Fails
- Check file format is supported
- Ensure file is under size limit
- Try a different browser
- Check internet connection
File Won't Connect
- Verify output type matches input type
- Image outputs (blue) → Image inputs
- Video outputs (purple) → Video inputs
- Audio outputs (orange) → Audio inputs
Poor Results from Upload
- Use higher quality source files
- Ensure good lighting in photos/videos
- Use clear audio without background noise
- Try a different AI model
Tips for Success
For Style Transfer
- Upload images with the style you want to capture
- Clear, recognizable style works best
- Avoid overly complex images
For Animation
- Choose images with natural poses
- Leave "room" for movement in composition
- Avoid images with extreme angles
For Voice Cloning
- Record in a quiet environment
- Speak naturally, not reading
- Include varied intonation
- Longer samples = better cloning
Next Steps
- Tool Nodes — Process your uploads
- Image Nodes — Transform your images
- Video Nodes — Animate your content