Skip to main content
Glama
Hermoso

Hermoso

Official

Restyle a video

restyle_video

Redraw every frame of a clip into a new visual look from presets or your own images while preserving its shots, motion, camera, timing, and sound.

Instructions

RESTYLE a clip into a new LOOK: every frame redrawn, shots, motion, camera, framing, timing and sound kept. Looks: Restyle looks in hermoso_capabilities (claymation, knitted yarn, cel-shaded CG anime…), your own words, or a look BUILT FROM YOUR IMAGES (styleImages); characters draws your own characters in. engine auto (default) picks by what is in the clip: a real-looking person -> kling (Kling 4.0 Edit, 3-15s); none -> wan (Wan 3.0, recommended, ≤15s) else seedance (Seedance 2.5, 4-30s); wan-prime = Wan 3.0 Prime by name (costs more). Paid; dryRun quotes it. One change only: edit_video.

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": {
      "video": "<video>"
    },
    "name": "restyle_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNoa look id from hermoso_capabilities (e.g. claymation, knitted-yarn, cel-shaded-anime-cg)
videoYesthe source video URL (a render, job result or list_library)
engineNodefault auto
describeNoa look in the user’s own words, when no preset fits, or extra detail on top of a preset
get_costNotrue: return the price only; nothing runs or bills
faceRouteNo'face_lane' = the user's "I own the rights to this face" for a real person in the source clip (paid plans). Only on the user's say-so, never on your own.
charactersNocharacters to draw the people as. Using a real person’s face, likeness or voice confirms you are them or have their consent, take full, unlimited responsibility for its use and will cover any claim against Hermoso (hermoso.ai/terms). Paid plan only; recorded.
resolutionNoSeedance and Wan; default 1080p
styleImagesNopictures that ARE the look (their style, never their subject)
idempotency_keyNochosen once, resent unchanged on retries: the same key never buys twice
expected_creditsNothe get_cost price; refused unbilled if the live price differs

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.1.532
    • addedInput schema / properties / expected_credits
      Added value: +{
      +  "description": "the get_cost price; refused unbilled if the live price differs",
      +  "type": "number"
      +}
    • addedInput schema / properties / get_cost
      Added value: +{
      +  "description": "true: return the price only; nothing runs or bills",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / idempotency_key
      Added value: +{
      +  "description": "chosen once, resent unchanged on retries: the same key never buys twice",
      +  "type": "string"
      +}
  2. Changed1 schema field changedv0.1.435
    • changedInput schema / properties / engine / enum
      Previous value: -[
      -  "auto",
      -  "seedance",
      -  "wan",
      -  "kling"
      -]New value: +[
      +  "auto",
      +  "seedance",
      +  "wan",
      +  "wan-prime",
      +  "kling"
      +]
  3. Changed6 schema fields changedv0.1.374
    • addedInput schema / properties / characters
      Added value: +{
      +  "description": "characters to draw the people as. Using a real person’s face, likeness or voice confirms you are them or have their consent, take full, unlimited responsibility for its use and will cover any claim against Hermoso (hermoso.ai/terms). Paid plan only; recorded.",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 4,
      +  "type": "array"
      +}
    • addedInput schema / properties / engine
      Added value: +{
      +  "description": "default auto",
      +  "enum": [
      +    "auto",
      +    "seedance",
      +    "wan",
      +    "kling"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / faceRoute
      Added value: +{
      +  "description": "'face_lane' = the user's \"I own the rights to this face\" for a real person in the source clip (paid plans). Only on the user's say-so, never on your own.",
      +  "enum": [
      +    "face_lane"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / resolution
      Added value: +{
      +  "description": "Seedance and Wan; default 1080p",
      +  "enum": [
      +    "480p",
      +    "720p",
      +    "1080p"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / style / description
      Previous value: -"a look id from hermoso_capabilities (e.g. claymation, vhs-80s, film-noir)"New value: +"a look id from hermoso_capabilities (e.g. claymation, knitted-yarn, cel-shaded-anime-cg)"
    • addedInput schema / properties / styleImages
      Added value: +{
      +  "description": "pictures that ARE the look (their style, never their subject)",
      +  "items": {
      +    "type": "string"
      +  },
      +  "maxItems": 9,
      +  "type": "array"
      +}
  4. Addedv0.1.372

TDQS

A4.5/5.0
Behavior4/5

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

Beyond the annotations (which only say non-read-only, open-world, non-idempotent, non-destructive) it discloses that the call is paid, that get_cost quotes without billing, duration limits per engine, plan gating for faceRoute and characters, and the consent/liability warning on real likenesses. What it does not disclose is what the call returns (job handle, render URL, storage in library) or how long a restyle typically takes, which matters for a paid long-running mutation.

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?

Dense and front-loaded, with the core transformation in the first clause and constraints after; almost every clause carries operational information. The telegraphic style ("characters draws your own characters in", "else seedance") is compressed to the point of being slightly ungrammatical, which costs a little readability.

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

Completeness4/5

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

For an 11-parameter, paid, open-world mutation with no output schema, the description covers cost, consent, engine selection, and idempotency expectations well. It still leaves the agent guessing about the return value and what happens to the source versus the produced render, which is the main remaining gap.

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

Parameters4/5

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

Schema coverage is already 100%, so the baseline is 3; the description still adds real meaning on top, notably the routing heuristic behind engine=auto, the per-engine duration envelopes, wan-prime's higher cost, and the crucial semantic that styleImages conveys the look and never the subject. One blemish: it says "dryRun quotes it" while the actual parameter is get_cost, a naming mismatch an agent must resolve itself.

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?

"RESTYLE a clip into a new LOOK: every frame redrawn, shots, motion, camera, framing, timing and sound kept" states a precise verb, resource and transformation scope, and explicitly carves out the boundary against the sibling ("One change only: edit_video"). An agent can distinguish it from edit_video, reframe_video or generate_video without opening any schema.

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

Usage Guidelines5/5

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

It gives explicit routing rules: engine auto picks by clip content (real person -> kling; none -> wan; else seedance), wan-prime is opt-in and costs more, and "One change only: edit_video" names the alternative and the condition that selects it for single edits. It also points to hermoso_capabilities for the preset look list, covering the discovery path.

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

Deploy Server

Other Tools