Spiral gives your agent every tool with one account. Browse the tools →

OpenClaw · Video

How to Use DWPose Video in OpenClaw

DWPose Video turns existing footage into pose visualization videos for movement review and animation reference. It works across a moving sequence, with body, hand, and facial pose views for different tasks.

Prompts to try with DWPose Video in OpenClaw

Copy an example into OpenClaw, or ask in your own words.

Each morning, use DWPose Video on newly submitted rehearsal video links. Create body pose views and add the results to the choreography review list.

DWPose VideoOpenClaw
Try asking
  • Every Friday, use DWPose Video on new gesture demonstration links. Create hand pose views for the animation team's review.

  • Each evening, use DWPose Video on newly submitted performance takes. Create facial pose views and pair each result with its original video link.

  • Every Monday, use DWPose Video on new exercise demonstration links. Create body pose views and place the results in the coach's review list.

  • Each day, use DWPose Video on new character movement reference links. Include body, hands, and face together and mark the results as awaiting manual review.

How to set up DWPose Video in OpenClaw

Pick the way that suits you. Each takes about two minutes.

Use the Spiral skill

  1. Send OpenClaw this message

    Your agent reads Spiral's skill and sets itself up.

    set up https://spiral.ai/SKILL.md
  2. Sign in or paste a key

    Approve Spiral in the browser, or give the agent a key from the console.

Use Spiral's MCP server

  1. Add the server

    On the machine that runs OpenClaw's Gateway:

    openclaw mcp add spiral \
      --url https://api.spiral.ai/mcp \
      --transport streamable-http \
      --auth oauth
  2. Sign in

    In Settings › MCP, select Sign in on the Spiral server, sign in to Spiral and click Authorize. No API key.

    openclaw mcp login spiral
  3. Reload and check

    A running Gateway may keep its old tool list: restart it, or Save & Publish in the Control UI.

    openclaw mcp reload
    openclaw mcp doctor spiral --probe

Use the Spiral CLI

  1. Install and sign in

    Installs the Spiral CLI, signs you in and adds its skill to your coding agents.

    npx -y spiral-cli@latest init

Call the Spiral API

  1. Create an API key

    In the console, under API keys.

  2. Run DWPose Video

    One request; the result comes back by polling or a webhook.

    curl https://api.spiral.ai/v1/runs \
      -H "Authorization: Bearer $SPIRAL_API_KEY" \
      -H "Content-Type: application/json" \
      -H "Idempotency-Key: $(uuidgen)" \
      -d '{
        "provider": "fal",
        "model": "fal-ai/dwpose/video",
        "input": {
          "video_url": "https://storage.googleapis.com/falserverless/gallery/Ben2/100063-video-2160.mp4"
        }
      }'

Then paste one of the prompts above: OpenClaw finds DWPose Video on Spiral, shows the price and runs it.

DWPose Video providers and prices

Spiral runs DWPose Video through fal. Open a card for today's price, with every fee included.

falVideo

Settings you can ask for

DWPose Video works from your video URL. Ask OpenClaw for any of these in your prompt.

SettingAllowed valuesDefaultDescription
Draw modefull-pose, body-pose, face-pose, hand-pose, face-hand-mask, face-mask, or hand-maskbody-pose

Mode of drawing the pose on the video. Options are: 'full-pose', 'body-pose', 'face-pose', 'hand-pose', 'face-hand-mask', 'face-mask', 'hand-mask'.

Every API field of DWPose Pose Prediction · Video to Pose is on its tool page: open its card above.

What can you do with DWPose Video in OpenClaw?

Prepare pose references whenever new footage arrives for review. A scheduled agent can process submitted video links and keep each result paired with its source.

Choreography reference

Extract body pose visuals from a dance rehearsal for a choreographer to review alongside the original footage.

Exercise movement review

Create a body pose view of an exercise demonstration for a coach to inspect.

Hand gesture reference

Extract hand pose visuals from a gesture demonstration for an animator to use as reference.

Facial movement reference

Create a facial landmark video from a performance take for visual review.

Character animation preparation

Prepare pose reference footage for a separate character animation workflow, reviewing the extraction before reuse.

Pose-guided image preparation

Extract a pose video, then select frames as references for a compatible ControlNet workflow.

Questions about DWPose Video in OpenClaw

Can OpenClaw use DWPose Video?

Yes. Add Spiral to OpenClaw as an MCP server, and OpenClaw can find and run DWPose Video like any built-in tool.

How much does DWPose Video cost in OpenClaw?

Up to $0.0468 per run at the default inputs for 60 seconds of input. You pay from your Spiral balance as you go, with no subscription, and a failed run is not charged. Your OpenClaw plan is separate.

Do I need a fal account to use DWPose Video in OpenClaw?

No. Spiral runs DWPose Video on its own fal account. You sign in to Spiral once and never paste a key.

How long does it take to set up DWPose Video in OpenClaw?

About two minutes: add the server, then sign in, then reload and check.

Does OpenClaw wait while DWPose Video runs?

DWPose Video runs in the background. OpenClaw starts the run, checks on it and gives you the video when it's ready.

What does DWPose Video produce?

It produces a pose visualization video from existing footage. Use the result to review movement or prepare a visual pose reference.

Can DWPose detect hands and faces?

Yes. DWPose estimates hand and facial landmarks alongside body keypoints, though the authors flag small hands and faces as challenging.

How should I choose which pose details to show?

Match the view to the task: body movement for choreography, hands for gesture reference, and facial landmarks for face movement. Include body, hands, and face together when you need their relationship.

Where should I check DWPose results most carefully?

Review moments when people overlap, body parts are hidden, or fingers form complex poses. The authors identify these as difficult cases for whole-body pose estimation.

Can DWPose poses guide image generation or character animation?

Yes. The official project documents ControlNet use and support for Animate Anyone character animation. Treat the pose video as a reference for a separate generation workflow.

Get started

Start using DWPose Video in OpenClaw

One Spiral account for every tool your agent needs. No subscription; you pay per run.

Paste this into OpenClaw:

Set up OpenClaw

set up https://spiral.ai/SKILL.md
Are you an AI agent? See setup options