Video from Image

Animate a single image into a dynamic video using Google DeepMind's Veo 3.1 model via fal.ai.

See references/fal-api.md for setup, Python patterns, and error handling.

API Endpoint

fal-ai/veo3.1/image-to-video

Parameters

Required

• prompt (string): Text description of the video motion and action to generate
• image_url (string): URL of the input image to animate (use fal_client.upload_file() for local files)

Optional

CLI Script

python3 scripts/fal_generate.py \
    --endpoint video-from-image \
    --prompt "Camera slowly pans across the landscape" \
    --image /path/to/photo.jpg \
    --duration 8s \
    --video-resolution 1080p \
    --output video.mp4

Tips

• Use descriptive motion language in prompts: pan, zoom, sway, flow, drift
• Describe camera movements for cinematic effects: "slow dolly forward", "aerial pull back"
• Higher resolution (1080p) gives better quality but takes longer and costs more
• Disable audio generation (generate_audio: False) to save credits when sound is not needed
• Ensure input image is at least 720p for best results
• Shorter duration (4s) generates faster and is good for quick previews