siyuan-note/siyuan · error

image model is not configured

Error message

image model is not configured

What it means

validateImageModel checks that both the resolved AI provider (conf.Provider) and the image-generation model (conf.Model) are non-nil. If either is missing — meaning no image-generation provider/model is configured in Settings - AI — it returns "image model is not configured". It then also validates the provider protocol.

Solutions

1. Open Settings - AI - Image generation and select a provider and model, then save
2. Verify Conf.AI.ImageGeneration has a valid provider with API key and an image-capable model name
3. In code, check Conf.AI.GetImageGenerationModel() for nil before calling GenerateImage to give a friendlier message
4. Re-add the provider entry if the referenced provider was removed from the provider list

Example fix

// before
provider, m := conf.Conf.AI.GetImageGenerationModel() // nil, nil
result, err := model.GenerateImage(ctx, req)
// after
provider, m := conf.Conf.AI.GetImageGenerationModel()
if provider == nil || m == nil { return errors.New("configure an image model in Settings - AI first") }
result, err = model.GenerateImage(ctx, req)

provider, m := conf.Conf.AI.GetImageGenerationModel()
if provider == nil || m == nil {
    return errors.New("select an image generation provider and model in Settings - AI first")
}

func imageModelConfigured() bool {
    p, m := conf.Conf.AI.GetImageGenerationModel()
    return p != nil && m != nil && p.APIKey != ""
}

res, err := model.GenerateImage(ctx, req)
if err != nil && err.Error() == "image model is not configured" {
    // direct the user to Settings - AI - Image generation instead of retrying
}

When it happens

Trigger: Conf.AI.GetImageGenerationModel() returns nil provider or nil model because the user never selected an image generation model, the configured provider was deleted, or the model list failed to load; calling GenerateImage on a fresh installation with default (empty) AI settings.

Common situations: Fresh install with no AI configuration; user configured a chat model but not an image model; config synced from a machine where the image model pointed to a provider that no longer exists; API key removed leaving the provider entry incomplete.

Understand the failure class

Background: "X is required", "must be set", "cannot be empty": the missing-required-config error family, from Vertex AI project/location to WeChat keys — this error's family across 18 libraries.

Related errors

• unsupported multimodal provider protocol
• AI configuration is unavailable
• generate image failed
• no AI editing config
• no AI editing model configured

AI-assisted analysis of siyuan-note/siyuan@9f775e8a12 (2026-09-19). Data as JSON: /api/errors/be871133f0768e14. Report an issue: GitHub.

Appendix: source

Thrown at kernel/model/assets.go:589

	return GenerateDocumentImageResult{
		Artifact: ImageArtifactRef{
			Kind: "image", Path: assetPath, MIMEType: generated.MIMEType, DocumentID: bt.RootID,
		},
		RevisedPrompt: generated.RevisedPrompt,
	}, nil
}

func resolveMultimodalDocument(documentID string) (*treenode.BlockTree, error) {
	bt := treenode.GetBlockTree(strings.TrimSpace(documentID))
	if bt == nil {
		return nil, errors.New("document not found: " + documentID)
	}
	return bt, nil
}

func validateImageModel(provider *conf.Provider, imageModel *conf.Model) error {
	if provider == nil || imageModel == nil {
		return errors.New("image model is not configured")
	}
	if provider.Protocol != "" && provider.Protocol != util.OpenAIProtocolChatCompletions &&
		provider.Protocol != util.OpenAIProtocolResponses {
		return fmt.Errorf("unsupported multimodal provider protocol: %s", provider.Protocol)
	}
	return nil
}

func documentReferencesImage(rootID, assetPath string) bool {
	paths, err := DocImageAssets(rootID)
	if err != nil {
		return false
	}
	wanted := AssetPathWithoutQuery(assetPath)
	for _, current := range paths {
		if AssetPathWithoutQuery(current) == wanted {
			return true
		}

View on GitHub (pinned to 9f775e8a12)