/agent-tools

Running Apps

Basic Run

belt app run user/app-name --input input.json

Inline JSON

belt app run falai/flux-dev-lora --input '{"prompt": "a sunset over mountains"}'

Version Pinning

belt app run user/app-name@1.0.0 --input input.json

Local File Uploads

The CLI automatically uploads local files when you provide a file path instead of a URL. Any field that accepts a URL also accepts a local path:

# Upscale a local image
belt app run falai/topaz-image-upscaler --input '{"image": "/path/to/photo.jpg", "upscale_factor": 2}'

# Image-to-video from local file
belt app run falai/wan-2-5-i2v --input '{"image": "./my-image.png", "prompt": "make it move"}'

# Avatar with local audio and image
belt app run bytedance/omnihuman-1-5 --input '{"audio": "/path/to/speech.mp3", "image": "/path/to/face.jpg"}'

# Post tweet with local media
belt app run x/post-create --input '{"text": "Check this out!", "media": ["./screenshot.png"]}'

Supported paths:

• Absolute paths: /home/user/images/photo.jpg
• Relative paths: ./image.png, ../data/video.mp4
• Home directory: ~/Pictures/photo.jpg

Generate Sample Input

Before running, generate a sample input file:

belt app sample falai/flux-dev-lora

Save to file:

belt app sample falai/flux-dev-lora --save input.json

Then edit input.json and run:

belt app run falai/flux-dev-lora --input input.json

Workflow Example

Image Generation with FLUX

# 1. Get app details
belt app get falai/flux-dev-lora

# 2. Generate sample input
belt app sample falai/flux-dev-lora --save input.json

# 3. Edit input.json
# {
#   "prompt": "a cat astronaut floating in space",
#   "num_images": 1,
#   "image_size": "landscape_16_9"
# }

# 4. Run
belt app run falai/flux-dev-lora --input input.json

Video Generation with Veo

# 1. Generate sample
belt app sample google/veo-3-1-fast --save input.json

# 2. Edit prompt
# {
#   "prompt": "A drone shot flying over a forest at sunset"
# }

# 3. Run
belt app run google/veo-3-1-fast --input input.json

Text-to-Speech

# Quick inline run
belt app run falai/kokoro-tts --input '{"prompt": "Hello, this is a test."}'

Task Tracking

When you run an app, the CLI shows the task ID:

Running falai/flux-dev-lora
Task ID: abc123def456

For long-running tasks, you can check status anytime:

# Check task status
belt task get abc123def456

# Get result as JSON
belt task get abc123def456 --json

# Save result to file
belt task get abc123def456 --save result.json

Run Without Waiting

For very long tasks, run in background:

# Submit and return immediately
belt app run google/veo-3-1 --input input.json --no-wait

# Check later
belt task get <task-id>

Output

The CLI returns the app output directly. For file outputs (images, videos, audio), you'll receive URLs to download.

Example output:

{
  "images": [
    {
      "url": "https://cloud.inference.sh/...",
      "content_type": "image/png"
    }
  ]
}

Error Handling

Documentation

• Running Apps - Complete running apps guide
• Streaming Results - Real-time progress updates
• Setup Parameters - Configuring app inputs