Image Generation with image_generate Tool

The image_generate tool generates and edits images using your configured providers. In chat sessions it operates asynchronously: OpenClaw registers a background task, returns the task ID immediately, and notifies the agent when the provider finishes. The completion agent follows the session's normal visible-reply mode: automatic final reply delivery when configured, or message(action="send") when the session requires the message tool. If the requesting session is inactive or its active wake fails, OpenClaw sends an idempotent direct fallback with the generated images so the result is not lost.

Note

The tool only appears when at least one image-generation provider is available. If you do not see image_generate in your agent's tools, configure agents.defaults.mediaModels.image, set up a provider API key, or sign in with OpenAI ChatGPT/Codex OAuth.

Quick start

Configure auth

Set an API key for at least one provider (for example OPENAI_API_KEY, GEMINI_API_KEY, OPENROUTER_API_KEY) or sign in with OpenAI Codex OAuth.

Pick a default model (optional)

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "openai/gpt-image-2",
        timeoutMs: 180_000,
      },
    },
  },
}

ChatGPT/Codex OAuth uses the same openai/gpt-image-2 model ref. When an openai OAuth profile is configured, OpenClaw routes image requests through that OAuth profile instead of first trying OPENAI_API_KEY. Explicit models.providers.openai config (API key, custom/Azure base URL) opts back into the direct OpenAI Images API route.

Ask the agent

"Generate an image of a friendly robot mascot."

The agent calls image_generate automatically. No tool allow-listing needed - it is enabled by default when a provider is available. The tool returns a background task id, then the completion agent sends the generated attachment through the message tool when it is ready.

Warning

For OpenAI-compatible LAN endpoints such as LocalAI, keep the custom models.providers.openai.baseUrl and explicitly opt in with browser.ssrfPolicy.dangerouslyAllowPrivateNetwork: true. Private and internal image endpoints remain blocked by default.

Common routes

The same tool handles text-to-image and reference-image editing. Use image for one reference or images for multiple. For Krea 2 models on fal, those references are sent as style references instead of edit inputs. Provider-supported output hints such as quality, outputFormat, and background are forwarded when available and reported as ignored when a provider does not declare support. Bundled transparent-background support is OpenAI-specific; other providers may still preserve PNG alpha if their backend emits it.

Supported providers

Use action: "list" to inspect available providers and models at runtime:

/tool image_generate action=list

Use action: "status" to inspect the active image-generation task for the current session:

/tool image_generate action=status

Provider capabilities

Tool parameters

• prompt (string, required), Image generation prompt. Required for action: "generate".

• action (generate" | "status" | "list, default: generate), Use "status" to inspect the active session task or "list" to inspect available providers and models at runtime.

• model (string), Provider/model override (e.g. openai/gpt-image-2). Use openai/gpt-image-1.5 for transparent OpenAI backgrounds.

• image (string), Single reference image path or URL for edit mode.

• images (string[]), Multiple reference images for edit mode or style-reference models (up to 14 through the shared tool; provider-specific limits still apply).

• size (string), Size hint: 1024x1024, 1536x1024, 1024x1536, 2048x2048, 3840x2160.

• aspectRatio (string), Aspect ratio: 1:1, 2:1, 20:9, 19.5:9, 2:3, 3:2, 2.35:1, 3:4, 4:3, 4:5, 5:4, 9:16, 9:19.5, 9:20, 16:9, 21:9, 1:2, 4:1, 1:4, 8:1, 1:8. Providers validate their model-specific subset.

• resolution (1K" | "2K" | "4K), Resolution hint.

• quality (low" | "medium" | "high" | "auto), Quality hint when the provider supports it.

• outputFormat (png" | "jpeg" | "webp), Output format hint when the provider supports it.

• background (transparent" | "opaque" | "auto), Background hint when the provider supports it. Use transparent with outputFormat: "png" or "webp" for transparency-capable providers.

• count (number), Number of images to generate (1-4).

• timeoutMs (number), Optional provider request timeout in milliseconds. When Codex calls image_generate through dynamic tools, this per-call value still overrides the configured default and is capped at 600000 ms.

• filename (string), Output filename hint.

• openai (object), OpenAI-only hints: background, moderation, outputCompression, and user.

• fal.creativity (raw" | "low" | "medium" | "high), fal Krea 2 creativity control. Defaults to medium.

Note

Not all providers support all parameters. When a fallback provider supports a nearby geometry option instead of the exact requested one, OpenClaw remaps to the closest supported size, aspect ratio, or resolution before submission. Unsupported output hints are dropped for providers that do not declare support and reported in the tool result. Tool results report the applied settings; details.normalization captures any requested-to-applied translation.

Configuration

Model selection

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "openai/gpt-image-2",
        timeoutMs: 180_000,
        fallbacks: [
          "openrouter/google/gemini-3.1-flash-image-preview",
          "google/gemini-3.1-flash-image",
          "fal/fal-ai/flux/dev",
        ],
      },
    },
  },
}

Provider selection order

OpenClaw checks providers in this sequence:

1. model parameter from the tool call (if the agent provides one).
2. imageGenerationModel.primary from configuration.
3. imageGenerationModel.fallbacks in order.
4. Auto-detection - only auth-backed provider defaults:
   • current default provider first;
   • remaining registered image-generation providers sorted by provider ID.

When a provider fails (auth error, rate limit, etc.), OpenClaw automatically tries the next configured candidate. If every candidate fails, the error message includes details from each attempt.

Per-call model overrides are exact

A per-call model override attempts only that specific provider and model and does not fall back to the configured primary, fallback, or auto-detected providers.

Auto-detection is auth-aware

A provider default only enters the candidate list when OpenClaw can successfully authenticate that provider. Automatic fallback across authenticated providers is always on; a per-call model remains authoritative.

Timeouts

Set agents.defaults.mediaModels.image.timeoutMs for slow image backends. A per-call timeoutMs tool parameter overrides the configured default, and configured defaults override plugin-authored provider defaults. Google and OpenRouter hosted image providers use 180 second defaults; Microsoft Foundry MAI, xAI, and Azure OpenAI image generation use 600 seconds. Codex dynamic-tool calls use a 120 second image_generate bridge default and honor the same timeout budget when configured, bounded by OpenClaw's 600000 ms dynamic-tool bridge maximum.

Inspect at runtime

Use action: "list" to see the currently registered providers, their default models, and auth environment variable hints.

Image editing

OpenAI, OpenRouter, Google, DeepInfra, fal, Microsoft Foundry, MiniMax, ComfyUI, and xAI support editing reference images. Krea 2 models on fal use the same image / images fields as style references instead of edit inputs. Pass a reference image path or URL:

"Generate a watercolor version of this photo" + image: "/path/to/photo.jpg"

OpenAI, OpenRouter, and Google support up to 5 reference images via the images parameter; xAI supports up to 3. fal supports 1 reference image for Flux image-to-image, up to 10 for GPT Image 2 edits, up to 10 style references for Krea 2, and up to 14 for Nano Banana 2 edits. Microsoft Foundry, MiniMax, and ComfyUI support 1.

Provider deep dives

OpenAI gpt-image-2 (and gpt-image-1.5)

OpenAI image generation defaults to openai/gpt-image-2. If an openai OAuth profile is configured, OpenClaw reuses the same OAuth profile used by Codex subscription chat models and sends the image request through the Codex Responses backend. Legacy Codex base URLs such as https://chatgpt.com/backend-api are canonicalized to https://chatgpt.com/backend-api/codex for image requests. OpenClaw does not silently fall back to OPENAI_API_KEY for that request. To force direct OpenAI Images API routing, configure models.providers.openai explicitly with an API key, custom base URL, or Azure endpoint.

The openai/gpt-image-1.5, openai/gpt-image-1, and openai/gpt-image-1-mini models can still be selected explicitly. Use gpt-image-1.5 for transparent-background PNG/WebP output; the current gpt-image-2 API rejects background: "transparent".

gpt-image-2 supports both text-to-image generation and reference-image editing through the same image_generate tool. OpenClaw forwards prompt, count, size, quality, outputFormat, and reference images to OpenAI. OpenAI does not receive aspectRatio or resolution directly; when possible OpenClaw maps those into a supported size, otherwise the tool reports them as ignored overrides.

OpenAI-specific options live under the openai object:

{
  "quality": "low",
  "outputFormat": "jpeg",
  "openai": {
    "background": "opaque",
    "moderation": "low",
    "outputCompression": 60,
    "user": "end-user-42"
  }
}

openai.background accepts transparent, opaque, or auto; transparent outputs require outputFormat png or webp and a transparency-capable OpenAI image model. OpenClaw routes default gpt-image-2 transparent-background requests to gpt-image-1.5. openai.outputCompression applies to JPEG/WebP outputs and is ignored for PNG outputs.

The top-level background hint is provider-neutral and currently maps to the same OpenAI background request field when the OpenAI provider is selected. Providers that do not declare background support return it in ignoredOverrides instead of receiving the unsupported parameter.

To route OpenAI image generation through an Azure OpenAI deployment instead of api.openai.com, see Azure OpenAI endpoints.

Microsoft Foundry MAI image models

Microsoft Foundry image generation uses deployed MAI image deployment names under the microsoft-foundry/ provider prefix. There is no provider-level default model because the MAI API expects your deployment name in the model field:

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "microsoft-foundry/<deployment-name>",
        timeoutMs: 600_000,
      },
    },
  },
}

The provider uses Microsoft Foundry's MAI API, not the OpenAI Images API:

• Generation endpoint: /mai/v1/images/generations
• Edit endpoint: /mai/v1/images/edits
• Auth: AZURE_OPENAI_API_KEY / provider API key, or Entra ID through az login
• Output: one PNG image
• Size: default 1024x1024; width and height must each be at least 768 px, and total pixels must be at most 1,048,576
• Edits: one PNG or JPEG reference image, supported only by MAI-Image-2.5-Flash and MAI-Image-2.5 deployments

Prompt-only generation can use a custom deployment name with just the Foundry endpoint configured. Edits with custom deployment names need onboarding/model metadata so OpenClaw can verify that the deployment is backed by MAI-Image-2.5-Flash or MAI-Image-2.5.

Current MAI image models are MAI-Image-2.5-Flash, MAI-Image-2.5, MAI-Image-2e, and MAI-Image-2. See Microsoft Foundry plugin for setup and chat-model behavior.

OpenRouter image models

OpenRouter image generation uses the same OPENROUTER_API_KEY and routes through OpenRouter's chat completions image API. Select OpenRouter image models with the openrouter/ prefix:

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "openrouter/google/gemini-3.1-flash-image-preview",
      },
    },
  },
}

OpenClaw forwards prompt, count, reference images, and Gemini-compatible aspectRatio / resolution hints to OpenRouter. Current built-in OpenRouter image model shortcuts include google/gemini-3.1-flash-image, google/gemini-3-pro-image, and openai/gpt-5.4-image-2. Use action: "list" to see what your configured plugin exposes.

fal Krea 2

Krea 2 models on fal use fal's native Krea schema instead of the generic image_size schema used by Flux. OpenClaw sends:

• aspect_ratio for aspect-ratio hints
• creativity, defaulting to medium
• image_style_references when image or images are supplied

Select Krea 2 Medium for faster expressive illustration and Krea 2 Large for slower, more detailed photoreal and textured looks:

{
  agents: {
    defaults: {
      imageGenerationModel: {
        primary: "fal/krea/v2/medium/text-to-image",
      },
    },
  },
}

Krea 2 currently returns one image per request. Prefer aspectRatio for Krea; OpenClaw maps size to the closest supported Krea aspect ratio and rejects resolution for Krea rather than dropping it. Use fal.creativity when you want a native Krea creativity level:

{
  "model": "fal/krea/v2/medium/text-to-image",
  "prompt": "A cyber zine portrait with risograph texture",
  "aspectRatio": "9:16",
  "fal": {
    "creativity": "high"
  }
}

MiniMax dual-auth

MiniMax image generation is available through both bundled MiniMax auth paths:

• minimax/image-01 for API-key setups
• minimax-portal/image-01 for OAuth setups

xAI grok-imagine-image

The bundled xAI provider uses /v1/images/generations for prompt-only requests and /v1/images/edits when image or images is present.

• Models: xai/grok-imagine-image, xai/grok-imagine-image-quality
• Count: up to 4
• References: one image or up to three images
• Aspect ratios: 1:1, 16:9, 9:16, 4:3, 3:4, 3:2, 2:3, 2:1, 1:2, 19.5:9, 9:19.5, 20:9, 9:20
• Resolutions: 1K, 2K
• Outputs: returned as OpenClaw-managed image attachments

OpenClaw intentionally does not expose xAI-native quality, mask, user, or the auto aspect ratio until those controls exist in the shared cross-provider image_generate contract.

Examples

Generate (4K landscape)

/tool image_generate action=generate model=openai/gpt-image-2 prompt="A clean editorial poster for OpenClaw image generation" size=3840x2160 count=1

Generate (transparent PNG)

/tool image_generate action=generate model=openai/gpt-image-1.5 prompt="A simple red circle sticker on a transparent background" outputFormat=png background=transparent

Equivalent CLI:

openclaw infer image generate \
  --model openai/gpt-image-1.5 \
  --output-format png \
  --background transparent \
  --prompt "A simple red circle sticker on a transparent background" \
  --json

Generate (OpenAI low quality)

/tool image_generate action=generate model=openai/gpt-image-2 prompt="Low-cost draft poster for a quiet productivity app" quality=low openai='{"moderation":"low"}'

Equivalent CLI:

openclaw infer image generate \
  --model openai/gpt-image-2 \
  --quality low \
  --openai-moderation low \
  --prompt "Low-cost draft poster for a quiet productivity app" \
  --json

Generate (two square)

/tool image_generate action=generate model=openai/gpt-image-2 prompt="Two visual directions for a calm productivity app icon" size=1024x1024 count=2

Edit (one reference)

/tool image_generate action=generate model=openai/gpt-image-2 prompt="Keep the subject, replace the background with a bright studio setup" image=/path/to/reference.png size=1024x1536

Edit (multiple references)

/tool image_generate action=generate model=openai/gpt-image-2 prompt="Combine the character identity from the first image with the color palette from the second" images='["/path/to/character.png","/path/to/palette.jpg"]' size=1536x1024

Krea style references

/tool image_generate action=generate model=fal/krea/v2/medium/text-to-image prompt="An expressive editorial portrait using this color palette and print texture" images='["/path/to/palette.png","/path/to/texture.jpg"]' aspectRatio=9:16 fal='{"creativity":"high"}'

The same --output-format, --background, --quality, and --openai-moderation flags are available on openclaw infer image edit; --openai-background remains as an OpenAI-specific alias. Bundled providers other than OpenAI do not declare explicit background control today, so background: "transparent" is reported as ignored for them.

Related

• Tools overview - all available agent tools
• ComfyUI - local ComfyUI and Comfy Cloud workflow setup
• fal - fal image and video provider setup
• Google (Gemini) - Gemini image provider setup
• Microsoft Foundry plugin - Microsoft Foundry chat and MAI image setup
• MiniMax - MiniMax image provider setup
• OpenAI - OpenAI Images provider setup
• Vydra - Vydra image, video, and speech setup
• xAI - Grok image, video, search, code execution, and TTS setup
• Configuration reference - imageGenerationModel config
• Models - model configuration and failover