generate-ai-image
Create AI-generated images from text prompts using specified models and parameters for visual content production.
Instructions
Generate AI images from text prompts.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| model | Yes | Model to use for generation | |
| input | Yes | Model-specific parameters |
Implementation Reference
- src/index.ts:970-985 (handler)The handler function for the 'generate-ai-image' tool. It proxies the request to the Dumpling AI API endpoint `/api/v1/generate-ai-image` using the provided model and input parameters, and returns the JSON response as text content.
async ({ model, input }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/generate-ai-image`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ model, input }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } - src/index.ts:955-969 (schema)Zod schema defining the input parameters for the 'generate-ai-image' tool: 'model' (required string) and 'input' (object with prompt, seed, num_outputs, etc.).
{ model: z.string().describe("Model to use for generation"), input: z .object({ prompt: z.string().describe("Text prompt"), seed: z.number().optional().describe("Random seed"), num_outputs: z.number().optional().describe("Number of images"), aspect_ratio: z.string().optional().describe("Aspect ratio"), output_format: z.string().optional().describe("Output format"), output_quality: z.number().optional().describe("Output quality"), num_inference_steps: z.number().optional().describe("Inference steps"), guidance: z.number().optional().describe("Guidance scale"), }) .describe("Model-specific parameters"), }, - src/index.ts:952-986 (registration)The server.tool() call that registers the 'generate-ai-image' tool, including its name, description, input schema, and inline handler function.
server.tool( "generate-ai-image", "Generate AI images from text prompts.", { model: z.string().describe("Model to use for generation"), input: z .object({ prompt: z.string().describe("Text prompt"), seed: z.number().optional().describe("Random seed"), num_outputs: z.number().optional().describe("Number of images"), aspect_ratio: z.string().optional().describe("Aspect ratio"), output_format: z.string().optional().describe("Output format"), output_quality: z.number().optional().describe("Output quality"), num_inference_steps: z.number().optional().describe("Inference steps"), guidance: z.number().optional().describe("Guidance scale"), }) .describe("Model-specific parameters"), }, async ({ model, input }) => { const apiKey = process.env.DUMPLING_API_KEY; if (!apiKey) throw new Error("DUMPLING_API_KEY not set"); const response = await fetch(`${NWS_API_BASE}/api/v1/generate-ai-image`, { method: "POST", headers: { "Content-Type": "application/json", Authorization: `Bearer ${apiKey}`, }, body: JSON.stringify({ model, input }), }); if (!response.ok) throw new Error(`Failed: ${response.status} ${await response.text()}`); const data = await response.json(); return { content: [{ type: "text", text: JSON.stringify(data, null, 2) }] }; } );