FlowiseAI/Flowise · error · Error

This model does not support images

Error message

This model does not support images

What it means

Thrown inside _getStandardContentBlockConverter().fromStandardImageBlock (line 133) when an image block is supplied to a non-multimodal Gemini model. isMultimodalModel is a boolean captured when the converter is built from the chat model's _isMultimodalModel flag; text-only Gemini variants (e.g., gemini-1.0 text models) set it false.

Source

Thrown at packages/components/nodes/chatmodels/ChatGoogleGenerativeAI/FlowiseChatGoogleGenerativeAI.ts:133

function _getStandardContentBlockConverter(isMultimodalModel: boolean) {
    const standardContentBlockConverter: StandardContentBlockConverter<{
        text: TextPart
        image: FileDataPart | InlineDataPart
        audio: FileDataPart | InlineDataPart
        file: FileDataPart | InlineDataPart | TextPart
    }> = {
        providerName: 'Google Gemini',

        fromStandardTextBlock(block) {
            return {
                text: block.text
            }
        },

        fromStandardImageBlock(block): FileDataPart | InlineDataPart {
            if (!isMultimodalModel) {
                throw new Error('This model does not support images')
            }
            if (block.source_type === 'url') {
                const data = parseBase64DataUrl({ dataUrl: block.url })
                if (data) {
                    return {
                        inlineData: {
                            mimeType: data.mime_type,
                            data: data.data
                        }
                    }
                } else {
                    return {
                        fileData: {
                            mimeType: block.mime_type ?? '',
                            fileUri: block.url
                        }
                    }
                }

View on GitHub (pinned to abe4a8601a)

Solutions

1. Switch the ChatGoogleGenerativeAI node to a multimodal model (e.g., gemini-1.5-pro, gemini-2.0-flash).
2. Remove image content from the messages feeding this node, or route images through a separate vision node.
3. Confirm the model identifier string actually resolves to a multimodal variant.

Example fix

// before: model = 'gemini-1.0'  + image block -> throws
// after:  model = 'gemini-2.0-flash' + image block -> supported

// Multimodal-capable Gemini model prefixes (extend as new models ship).
const MULTIMODAL_PREFIXES = ['gemini-1.5', 'gemini-2', 'gemini-3']
function isMultimodalGemini(model: string): boolean {
  return MULTIMODAL_PREFIXES.some((p) => model.startsWith(p))
}
if (hasImageBlock(messages) && !isMultimodalGemini(model)) {
  throw new Error(`Model ${model} cannot accept images; use a multimodal variant`)
}

function hasImageBlock(messages: BaseMessage[]): boolean {
  return messages.some((m) => Array.isArray(m.content) && m.content.some((c) => (c as any).type === 'image_url' || (c as any).type === 'image'))
}

try {
  await chatModel.invoke(messages)
} catch (e) {
  if (e instanceof Error && e.message === 'This model does not support images') {
    // switch to a multimodal model or strip image parts
  }
  throw e
}

When it happens

Trigger: A standard image content block (source_type url/base64) is converted to a provider block while isMultimodalModel is false.

Common situations: User selected a text-only Gemini model in the node but the chatflow passes image content, or a model was downgraded from a vision-capable variant.

Related errors

• Unsupported source type: ${block.source_type}
• This model does not support audio
• This model does not support files
• Please provide image as base64 encoded data URL
• Invalid media content

AI-assisted analysis of FlowiseAI/Flowise@abe4a8601a (2026-08-12). Data as JSON: /api/errors/0bbee26da0020ecd. Report an issue: GitHub.