MCP/Tools/Images/generate_variations
generate_variations

Generate variations of a reference image

High cost

Upload a reference creative, get N variant concepts back that keep the structural framing but vary the vehicle / background / headline / CTA / colors.

How it works

Two-phase tool. First the agent passes a reference image (URL or base64) plus what to vary; the tool runs a vision pass, produces N concept prompts, and returns them immediately. The agent then renders each concept via generate_image (one call per variant, supports multi-aspect). Perfect for taking a winning ad and producing 10 variants for A/B testing without losing the visual DNA.

Inputs

Name
Type
Required
Description
referenceImageUrl
string
optional
URL of the reference image. Preferred for Claivra-hosted images.
referenceImageBase64
string
optional
Base64 reference for images not reachable by URL.
count
integer (2–10)
optional
How many variant concepts to produce. Default 5.
varyOptions
string[]
optional
What to vary — vehicle, background, headline, cta, colors.
aspectRatios
string[]
optional
Aspect ratios to render each variant at. Default [1:1].
notes
string
optional
Extra direction for the vision/variant prompts.
profileId
string
optional
Niche profile applied to the variant prompts.
brandId
string
optional
Brand kit woven into the variants.

Returns

{ concepts: [{ name, imagePrompt, cta, headline, body }], requestedAspectRatios } — agent then calls generate_image per concept.

Examples

5 variants of a winning ad, square + Google Ad sizes

Plug Motors had a winning Tesla creative. Agent generates 5 variants for next week's test, each in both sizes.

{
  "referenceImageUrl": "https://cdn.claivra.com/file/claivra/.../tesla-winner.jpeg",
  "count": 5,
  "varyOptions": [
    "vehicle",
    "background",
    "headline"
  ],
  "aspectRatios": [
    "1:1",
    "1.91:1"
  ],
  "brandId": "aBmbZETe9gUZhwXHCE02",
  "notes": "Keep the green spotlight + reflective floor — those are the brand cues that work."
}