Skip to main content
Glama

Text to image (Fluw AI)

luw_generate_image

Generate photorealistic images or vector illustrations from text prompts, optionally using a guide image, for concept art, interiors, products, and marketing visuals.

Instructions

Luw.ai Fluw AI: generate a photorealistic image or illustration from a text prompt (optionally guided by an input image) — concept art, interiors, products, marketing visuals. Set format="svg" for a vector illustration (Fluw Vector AI). Costs 2 credits per image.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prompt": "<prompt>"
    },
    "name": "luw_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoSame seed and prompt give the same image. Text-to-image only: ignored with a guide image or svg.
imageNoOptional guide image (public https:// link or data: URI; the local npx server also accepts a file path).
formatNoOutput format; svg switches to Fluw Vector AI, which ignores aspect_ratio and seed.
promptYesWhat to generate.
stylesNoDesign style names, e.g. ["Scandinavian"]; for Japandi use ["Japanese Design", "Scandinavian"]. Case-sensitive; see luw_list_options.
variationsNoNumber of alternative designs (1-4, default 1); each is billed as a generation.
aspect_ratioNoPicture shape; 3:2 and 2:3 come out as 4:3 and 3:4.
enhance_promptNoLet Luw.ai's prompt enhancer expand a short prompt.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.3.18
    • addedInput schema / properties / aspect_ratio / description
      Added value: +"Picture shape; 3:2 and 2:3 come out as 4:3 and 3:4."
    • removedInput schema / properties / engine
      Removed value: -{
      -  "description": "Luw.ai model: aria (default) or symphony (Symphony-3).",
      -  "enum": [
      -    "aria",
      -    "symphony"
      -  ],
      -  "type": "string"
      -}
    • changedInput schema / properties / format / description
      Previous value: -"Output format; svg switches to Fluw Vector AI."New value: +"Output format; svg switches to Fluw Vector AI, which ignores aspect_ratio and seed."
    • changedInput schema / properties / image / description
      Previous value: -"Optional guide image (https:// URL, local file path, or data: URI)."New value: +"Optional guide image (public https:// link or data: URI; the local npx server also accepts a file path)."
    • changedInput schema / properties / seed / description
      Previous value: -"Fix for reproducible results."New value: +"Same seed and prompt give the same image. Text-to-image only: ignored with a guide image or svg."
  2. Changed1 schema field changedv0.3.2
    • changedInput schema / properties / styles / description
      Previous value: -"Design style names, e.g. [\"Japandi\"]. Case-sensitive; see luw_list_options."New value: +"Design style names, e.g. [\"Scandinavian\"]; for Japandi use [\"Japanese Design\", \"Scandinavian\"]. Case-sensitive; see luw_list_options."
  3. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare openWorldHint=true and destructiveHint=false, so this is understood as a non-destructive generative call. The description adds cost information (2 credits per image) that the annotations do not carry, which is materially useful. It does not say how the result comes back (direct image vs. a job id requiring luw_get_result), leaving the biggest operational question unanswered.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tight sentences with the core action front-loaded and the cost caveat last. The first sentence is dense with parentheses and em dashes but every clause (modality, optional guide image, use cases) carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-parameter generative tool with no output schema, the definition covers inputs and billing but not the response contract — whether an image URL is returned inline or an async job must be polled. That omission matters given a get-result sibling in the catalog.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so seed, image, format, styles, variations, aspect_ratio, and enhance_prompt are all documented in the schema, including the svg/seed interaction. The description restates the format="svg" behavior and the optional guide image but adds no semantics beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb (generate) plus resource (image/illustration) and a clear input modality (text prompt, optionally guided by an input image). It even names a within-tool variant (format="svg" routes to Fluw Vector AI), so an agent can tell this apart from edit/expand/upscale-style siblings that operate on an existing image.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete application contexts (concept art, interiors, products, marketing visuals) that imply when to pick this over the other Luw.ai siblings, and explains the svg escape hatch. It stops short of explicit exclusion language such as "for modifying an existing photo use luw_edit_image."

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.