Topaz · Utility

Hermes Agent x Topaz

Topaz Labs specializes in AI media enhancement with dedicated image and video upscaling models. Through RunAPI, both upscale endpoints share unified billing.

2 variants from $0.14 / second Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use topaz-upscale-image when it matches the task: Neural image upscaling; recovers detail without artifacts.

You have access to RunAPI task tools for Topaz.

Available Topaz models:
- topaz-upscale-image: Neural image upscaling; recovers detail without artifacts
  endpoints: /api/v1/topaz/upscale_image
  request fields: model, source_image_url, upscale_factor
- topaz-upscale-video: Frame-by-frame video upscaling with temporal consistency
  endpoints: /api/v1/topaz/upscale_video
  request fields: model, source_video_url

Use the model ID and endpoint that match the user's request.
Example prompt: Upscale this 720p product photo to 4K while preserving fine texture detail and removing noise.
/api/v1/topaz/upscale_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/topaz/upscale_image and save the returned Task id.
GET /api/v1/topaz/upscale_image/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.
/api/v1/topaz/upscale_video: Submit the task, poll for its status, then verify the completed output. POST /api/v1/topaz/upscale_video and save the returned Task id.
GET /api/v1/topaz/upscale_video/<task-id> until status is completed or failed.
Verify the completed response contains the endpoint-specific output documented in the API reference.

Public Versions and Endpoints

Model ID Endpoints Price Catalog
topaz-upscale-image
/api/v1/topaz/upscale_image
$0.20 / call Model detail
topaz-upscale-video
/api/v1/topaz/upscale_video
$0.14 / second Model detail

Verify

Poll until the task reaches a terminal status

Select <model-id> to generate verification commands.

Configuration

Guide endpoint: <endpoint>

Select <model-id> to generate a request with the endpoint's public input contract.
How it works

Get Started in 3 Steps

  1. Choose a model ID

    Select a public catalog model ID and review its endpoint and current starting price.

  2. Configure RunAPI

    Set RUNAPI_API_KEY before making the endpoint request.

  3. Verify the result

    For asynchronous endpoints, poll the same endpoint until the Task reaches a terminal status.

What to Build with Hermes Agent + Topaz

  • Generation-to-print pipeline

    Generate an image with any RunAPI image model, then upscale it with Topaz in the same Hermes Agent workflow to reach print-ready resolution.

  • AI artifact cleanup

    Reduce compression artifacts, noise, and blur in AI-generated images before commercial use or client delivery.

  • Old photograph restoration

    Enhance scanned photos and archival images to modern display standards, recovering detail from low-resolution or degraded sources.

Why Use Topaz Through RunAPI + Hermes Agent

  • 2 variants, one API key

    Use one RunAPI connection to choose among the live model variants without changing your integration.

  • Clear usage pricing

    See current catalog pricing before you send a request, with no subscription or minimum spend required.

  • Automatic task workflows

    Submit, poll, and collect asynchronous results through a consistent task workflow without writing manual polling code.

Hermes Agent + Topaz Questions

Can I use Topaz in Hermes Agent?

Yes. Configure RunAPI as a provider in Hermes Agent, then ask the agent to call the Topaz endpoint shown on this page. The same provider used for chat handles upscaling.

When should I use Topaz instead of Recraft upscaling?

Topaz is aimed at photographic detail at large enlargements. Recraft upscaling is aimed at clean edges on design assets and product photos. Try both on a sample if you are unsure.

Does quality degrade on certain image types?

Topaz works best on photographic content. Heavily compressed images, very small sources, or images with existing AI artifacts can look over-smoothed at high scale factors, so test a smaller scale before running a batch.

Which model ID should I use?

Choose a public model ID from the version table. Each ID exposes the endpoints shown for that version.

Does this guide configure a chat model?

No. This Model Line uses the endpoint workflow shown here and is not presented as an agent chat model.

Start using Topaz with Hermes Agent

Get API Key Read Quickstart

Building with a team?

We're here to help with enterprise setup, integrations, and technical questions.

Contact Us