Skip to main content

​
Overview

CommandDescriptionCost
naive video generate <prompt>Generate video from text or image5–10 credits
naive video status <job_id>Check generation statusFree
naive video modelsList available modelsFree
Completed video generation jobs are auto-ingested to the Media Asset Manager. For video clipping commands (clip, clip-status, clip-edit), see the clips CLI reference.

​
Generate Video

Submits a video generation job. Videos take 30–120 seconds to generate.

​
Text-to-Video

naive video generate "a rocket launching into space" --model fal-ai/kling-video/v3/pro/text-to-video
naive video generate "timelapse of a flower blooming" --model fal-ai/kling-video/v3/pro/text-to-video --duration 10 --wait

​
Image-to-Video

naive video generate --model fal-ai/kling-video/v3/pro/image-to-video \
  --image-url https://example.com/photo.jpg

​
Advanced (full parameter passthrough)

naive video generate --model fal-ai/kling-video/v3/pro/image-to-video \
  --input '{"prompt":"zoom in slowly","image_url":"https://...","duration":"5","aspect_ratio":"16:9"}'

​
Options

FlagRequiredDescription
promptNo*Text description (positional argument)
--model <model>YesVideo model ID
--input <json>No*Full model parameters as JSON
--duration <seconds>NoVideo duration: "5" or "10" (model-dependent)
--image-url <url>NoSource image for image-to-video
--waitNoBlock until generation completes
*Either prompt, --image-url, or --input is required.

​
Model Parameters (via --input)

ParameterTypeModelsDescription
promptstringAllText description of the video
durationstringKlingDuration: "5" or "10" seconds
image_urlstringImage-to-videoSource image URL
aspect_ratiostringKling"16:9", "9:16", "1:1"
negative_promptstringKling text-to-videoWhat to avoid
cfg_scalenumberKlingGuidance 0-1 (default 0.5, higher = more literal)
generate_audiobooleanKling v3Enable native audio (default: true)

​
Output (submitted)

{
  "success": true,
  "action": "video.generate.submitted",
  "result": { "job_id": "job-uuid-123", "status": "queued", "model": "fal-ai/kling-video/v3/pro/text-to-video" },
  "next_steps": [
    { "command": "naive video status job-uuid-123", "description": "Check generation progress" },
    { "command": "naive jobs get job-uuid-123", "description": "Get full job details" }
  ],
  "hints": [
    "Video generation submitted",
    "Credits deducted only on successful completion",
    "Typical time: 30-120 seconds depending on model and duration"
  ]
}

​
Output (completed — with --wait)

{
  "success": true,
  "action": "video.generate.completed",
  "result": {
    "id": "job-uuid-123",
    "status": "completed",
    "result": {
      "video": { "url": "https://fal.media/files/.../video.mp4" }
    },
    "credits_used": 5
  },
  "next_steps": [
    { "command": "# Download: curl -o video.mp4 \"https://fal.media/files/.../video.mp4\"", "description": "Download the video" },
    { "command": "naive video generate \"another prompt\" --model <model>", "description": "Generate another video" }
  ],
  "hints": ["Video generation complete — download URL available"]
}

​
Available Models

ModelTypeTimeCost
fal-ai/kling-video/v3/pro/text-to-videotext-to-video~60s5 credits (5s) / 10 credits (10s)
fal-ai/kling-video/v3/pro/image-to-videoimage-to-video~60s5 credits (5s) / 10 credits (10s)
fal-ai/kling-video/v3/standard/text-to-videotext-to-video~45s5 credits
fal-ai/minimax-video/video-01-livetext-to-video~45s5 credits
fal-ai/wan/v2.7/text-to-videotext-to-video~60s5 credits
fal-ai/kling-video/v2.1/standard/image-to-videoimage-to-video~60s5 credits
Use naive video models for the full up-to-date list.

​
Check Status

naive video status <job-id>

{
  "success": true,
  "action": "video.status",
  "result": {
    "id": "job-uuid-123",
    "status": "running",
    "progress": 45,
    "type": "video_generation"
  },
  "next_steps": [
    { "command": "naive video status job-uuid-123", "description": "Check again in 10-30 seconds" }
  ],
  "hints": ["Job status: running", "Video generation typically takes 30-120 seconds"]
}

​
List Models

naive video models
Returns all supported video models with type (text-to-video or image-to-video), supported parameters, and timing estimates.

​
Credit Behavior

  • Credits are NOT reserved at submission time
  • Credits are deducted ONLY when the job completes successfully
  • Failed or cancelled video jobs cost nothing
  • Use naive usage to audit credit deductions