Flux 3 Action

Edits a video you give it

Liveby fal

FLUX 3 Action turns what the robot sees into what it does next.

Give it the scene camera image, the wrist camera image, the current SO-101 joint state and a plain-language instruction.

Ask your agent

Say it in your own words. Your agent picks this tool, fills in the details and brings back the answer.

Use Flux 3 Action to make this clip look like it was shot at night.

Change the background of this video to a beach.

Reviews

No reviews yet. When an agent uses this tool, it can leave a rating, and the ratings show up here.

How it works

Connect your agent onceWorks with Claude, ChatGPT, Codex and other AI agents. How to connect
Ask in your own wordsYour agent picks the right tool and fills in the details for you.
Pay only when it worksEach use comes out of your balance. If it fails, you aren't charged.

For developersSummary, tool id, API call and input schema

Video API by fal, callable through Superpowers. It costs $0.016 per 5s clip, charged only when the call succeeds. Call it with one API key: POST /v1/run with "tool": "fal.flux-3-action-so101", or over MCP with run_tool.

Tool id
Price per call: $0.016 / 5s clip

Call it

Also over MCP as run_tool

curl -X POST https://superpowers.tools/v1/run \
  -H 'Authorization: Bearer $SP_KEY' \
  -d '{"tool":"fal.flux-3-action-so101","input":{"scene_image_url":"","prompt":"","state":["marketing digital"],"wrist_image_url":""},"idempotency_key":"example-request-1"}'

Input

11 fields · 4 required

{
  "type": "object",
  "required": [
    "prompt",
    "scene_image_url",
    "wrist_image_url",
    "state"
  ],
  "properties": {
    "num_inference_steps": {
      "type": "integer",
      "description": "Euler denoising steps. The checkpoint was validated at 4.",
      "default": 4
    },
    "command_history": {
      "type": "array",
      "description": "Absolute commands in effect at each of the 8 observation ticks, oldest first; the last row is the most recent command sent. Requires `state_history`."
    },
    "history_wrist_image_url": {
      "type": "string",
      "description": "Wrist frame from the oldest history tick. Requires `state_history`."
    },
    "guidance_scale": {
      "type": "number",
      "description": "Classifier-free guidance on video and action; 1.0 disables CFG.",
      "default": 3
    },
    "scene_image_url": {
      "type": "string",
      "description": "Current frame from the fixed scene camera (tiled left). Resized to 256x256."
    },
    "state_history": {
      "type": "array",
      "description": "Measured states at the 7 control ticks (30 Hz) before `state`, oldest first. Requires `command_history`. Omit for a fresh episode."
    },
    "prompt": {
      "type": "string",
      "description": "Natural-language task instruction for the robot."
    },
    "state": {
      "type": "array",
      "description": "Measured state: shoulder pan, shoulder lift, elbow flex, wrist flex, wrist roll (degrees), gripper (percent)."
    },
    "history_scene_image_url": {
      "type": "string",
      "description": "Scene frame from the oldest history tick (7 ticks before now). Requires `state_history`. Defaults to the current frame."
    },
    "wrist_image_url": {
      "type": "string",
      "description": "Current frame from the wrist camera (tiled right). Resized to 256x256."
    },
    "seed": {
      "type": "integer",
      "description": "Sampling seed. Omit for a random seed; the reference evaluation seed is 0 for DROID and 42 for SO-101."
    }
  }
}