Integrate fal AI with OpenClaw: Quick Setup Guide

이 콘텐츠는 아직 번역되지 않았습니다.

Setting up hosted image and video generation often feels like a chore when you just want to build. You usually have to handle API keys and figure out model endpoints.

OpenClaw includes a built-in fal provider to handle this for you. It gives you direct access to high-end models for images and video without the usual integration friction.

Quick start

First, you need to get your credentials sorted. OpenClaw uses FAL_KEY as the main environment variable, but it recognizes FAL_API_KEY too.

Set the API key:

openclaw onboard --auth-choice fal-api-key

Set a default image model:

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "fal/fal-ai/flux/dev",
      },
    },
  },
}

Image generation

The bundled fal image-generation provider defaults to fal/fal-ai/flux/dev. It is a solid choice for most projects.

Generate: up to 4 images per request
Edit mode: enabled, 1 reference image
Supports size, aspectRatio, and resolution
Current edit caveat: the fal image edit endpoint does not support aspectRatio overrides

To use fal as the default image provider, update your config:

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "fal/fal-ai/flux/dev",
      },
    },
  },
}

Video generation

For video, the bundled provider defaults to fal/fal-ai/minimax/video-01-live. Since video takes time, it uses a queue-backed flow that handles the submit, status, and result steps.

Modes: text-to-video and single-image reference flows
Runtime: queue-backed submit/status/result flow for long-running jobs
HeyGen video-agent model ref:
fal/fal-ai/heygen/v2/video-agent
Seedance 2.0 model refs:
fal/bytedance/seedance-2.0/fast/text-to-video
fal/bytedance/seedance-2.0/fast/image-to-video
fal/bytedance/seedance-2.0/text-to-video
fal/bytedance/seedance-2.0/image-to-video

To use Seedance 2.0 as the default video model:

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "fal/bytedance/seedance-2.0/fast/text-to-video",
      },
    },
  },
}

To use HeyGen video-agent as the default video model:

{
  agents: {
    defaults: {
      videoGenerationModel: {
        primary: "fal/fal-ai/heygen/v2/video-agent",
      },
    },
  },
}

Need help getting this running? Check out the AI Setup Assistant.

Next steps

OpenClaw Expert

아직 막혀 있나요?

이 문서에서 답을 못 찾았다면 OpenClaw Expert에게 바로 물어보세요.