Omnia Media MCP

recreate_from_seed

Transform an existing image with an image-to-image diffusion pipeline, using a text prompt and adjustable strength to control how closely details are preserved or reimagined.

Instructions

Recreate or transform an existing image using an image-to-image diffusion pipeline with controllable strength.

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": {
      "seed_image": "<seed_image>",
      "prompt": "<prompt>"
    },
    "name": "recreate_from_seed"
  }
}

Input Schema

Name	Required	Description
`prompt`	Yes	Description of the target aesthetic, lighting, environment, or alterations.
`strength`	No	Transformation intensity (0.35 preserves close details, 0.75 is balanced, 0.90 is radical reimagining). Defaults to 0.75.
`seed_image`	Yes	Public HTTP/HTTPS URL, Base64 string, or Data URI of the starting image.
`aspect_ratio`	No	Output aspect ratio.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 6, 2026

TDQS

C2.9/5.0

Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It names the pipeline type and 'controllable strength' but says nothing about permissions, latency/cost, determinism, failure modes for bad URLs, or what the operation returns — all of which matter for a generative mutation tool.

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?

A single well-formed sentence with the core purpose front-loaded and no filler. 'Recreate or transform' is mildly redundant but the sentence is otherwise tight and scannable.

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?

Parameters are fully documented via the schema and there is no output schema to explain, so the structural side is adequate. However, with zero annotations, the description leaves the behavioral and selection-side gaps that an agent needs to invoke this correctly alongside its siblings.

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%, with strength guidance (0.35/0.75/0.90) and accepted seed_image formats already documented in the schema. The description only echoes 'controllable strength', adding no syntax or constraint detail beyond structured fields, so the baseline 3 applies.

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

Purpose4/5

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

States a specific verb set ('recreate or transform') and resource ('an existing image') and names the underlying mechanism (image-to-image diffusion pipeline). This implicitly distinguishes it from text-only generation siblings like generate_image, though no sibling is named explicitly.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not guidance. The phrase 'existing image' implies a seed image is required, but the description never tells the agent to prefer this over generate_image, remove_background, or stage_product, nor what conditions make it the wrong choice.

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

Deploy Server