Black Forest Labs · Image

Hermes Agent x Flux 2

Flux 2 is Black Forest Labs' generation model, delivering high prompt adherence across text-to-image and remix-image tasks. Through RunAPI, Pro and Flex variants share the same API shape.

6 variants from $0.07 / call Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use flux-2-flex-remix-image when it matches the task: Flex control + reference image input.

You have access to RunAPI task tools for Flux 2.

Available Flux 2 models:
- flux-2-flex-remix-image: Flex control + reference image input
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-flex-text-to-image: Adjustable steps + guidance; up to 8 source images via remix; best typography
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt
- flux-2-max-remix-image: Highest-quality FLUX.2 source-image remix with consistent edits
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls, aspect_ratio
- flux-2-max-text-to-image: Highest-quality FLUX.2 generation with strong prompt following
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt, aspect_ratio
- flux-2-pro-remix-image: Pro quality with input image as style/content seed
  endpoints: /api/v1/flux_2/remix_image
  request fields: model, prompt, source_image_urls
- flux-2-pro-text-to-image: Zero-config flagship; automatic prompt enhancement
  endpoints: /api/v1/flux_2/text_to_image
  request fields: model, prompt

Use the model ID and endpoint that match the user's request.
Example prompt: Generate a photorealistic studio portrait of an astronaut holding a cat, dramatic rim lighting, fine detail.
/api/v1/flux_2/remix_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/flux_2/remix_image and save the returned Task id.
GET /api/v1/flux_2/remix_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/flux_2/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/flux_2/text_to_image and save the returned Task id.
GET /api/v1/flux_2/text_to_image/<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
flux-2-flex-remix-image
/api/v1/flux_2/remix_image
$0.14 / call Model detail
flux-2-flex-text-to-image
/api/v1/flux_2/text_to_image
$0.14 / call Model detail
flux-2-max-remix-image
/api/v1/flux_2/remix_image
$0.15 / call Model detail
flux-2-max-text-to-image
/api/v1/flux_2/text_to_image
$0.15 / call Model detail
flux-2-pro-remix-image
/api/v1/flux_2/remix_image
$0.07 / call Model detail
flux-2-pro-text-to-image
/api/v1/flux_2/text_to_image
$0.07 / call 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 + Flux 2

  • Stock photography replacement

    Generate photorealistic product shots, lifestyle scenes, and architectural images on demand instead of licensing stock photos.

  • Character sheets for game developers

    Generate character reference sheets from several angles, with multi-reference conditioning keeping the design stable across poses.

  • E-learning instructor avatars

    Create consistent instructor avatars for online courses across many lesson thumbnails and slide illustrations.

Why Use Flux 2 Through RunAPI + Hermes Agent

  • 6 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 + Flux 2 Questions

Do I need local hardware to run Flux 2 from Hermes Agent?

No. Hermes Agent calls Flux 2 through the RunAPI API, and inference runs server-side, with no VRAM requirements, ComfyUI setup, or model downloads.

Do I need a separate provider for Flux 2 image generation?

No. The RunAPI provider you configured for chat already works for Flux 2 and all other RunAPI models.

Can Hermes Agent chain Flux 2 with editing or upscaling models?

Yes. Hermes Agent can generate with Flux 2, refine the result with an editing model, and upscale it, all in one workflow through the same RunAPI provider.

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 Flux 2 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