---
title: Use Flux 2 in WorkBuddy via RunAPI — MCP Image Guide | RunAPI
description: Generate images with Flux 2 by Black Forest Labs in WorkBuddy over MCP with RunAPI. Text-to-image and multi-source remix tools, called from the workbench.
url: https://runapi.ai/workbuddy-flux-2.md
canonical: https://runapi.ai/workbuddy-flux-2
locale: en
site: RunAPI
image: https://runapi.ai/assets/opengraph-bfaaa0f0.png
alternates:
  en: https://runapi.ai/workbuddy-flux-2
  zh-CN: https://runapi.ai/zh-CN/workbuddy-flux-2
  es: https://runapi.ai/es/workbuddy-flux-2
  ja: https://runapi.ai/ja/workbuddy-flux-2
  de: https://runapi.ai/de/workbuddy-flux-2
  fr: https://runapi.ai/fr/workbuddy-flux-2
  pt-BR: https://runapi.ai/pt-BR/workbuddy-flux-2
  ko: https://runapi.ai/ko/workbuddy-flux-2
  it: https://runapi.ai/it/workbuddy-flux-2
  nl: https://runapi.ai/nl/workbuddy-flux-2
  pl: https://runapi.ai/pl/workbuddy-flux-2
  tr: https://runapi.ai/tr/workbuddy-flux-2
  zh-TW: https://runapi.ai/zh-TW/workbuddy-flux-2
  zh-HK: https://runapi.ai/zh-HK/workbuddy-flux-2
  ar: https://runapi.ai/ar/workbuddy-flux-2
  x-default: https://runapi.ai/workbuddy-flux-2
model: flux-2
---

> HTML version: https://runapi.ai/workbuddy-flux-2
> Site index for agents: https://runapi.ai/llms.txt


# Use Flux 2 in WorkBuddy.

Flux 2 by Black Forest Labs comes in several quality versions, from faster generation to higher-fidelity output. Every version supports text-to-image and multi-source remix, and the Flux 2 model catalog lists each version with its resolutions and current pricing. WorkBuddy calls them as tools on the RunAPI MCP server, right from the workbench.

- [Get API Key](https://runapi.ai/login)
- [Read the docs](https://runapi.ai/docs/guides)

one API key · text to image + remix tools · 1k / 2k resolution (Max: 1k only)

### Prompt

```text
Use the runapi MCP server to generate an image with Flux 2 Pro.

Requirements:
- Call the RunAPI text_to_image tool with model "flux-2-pro-text-to-image"
- Prompt: a ceramic vase with dried flowers on a linen tablecloth, natural window light, 35mm film grain
- Set aspect_ratio to "3:4" and output_resolution to "2k"
- Wait for the task to complete and show me the image URL

```

### MCP config

```bash
{
  "mcpServers": {
    "runapi": {
      "url": "https://runapi.ai/mcp",
      "transport": "streamable_http",
      "headers": {
        "Authorization": "Bearer ${RUNAPI_API_KEY}"
      }
    }
  }
}

```

### Response

```json
{
  "task_id": "tsk_abc123",
  "status": "completed",
  "model": "flux-2-pro-text-to-image",
  "output": {
    "image_url": "https://media.runapi.ai/outputs/tsk_abc123.png"
  }
}

```

## Use Flux 2 in WorkBuddy in three steps

1. **Add the RunAPI MCP server** - Register an MCP server named runapi in WorkBuddy, pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected for chat, Flux 2 is exposed on the same server — no extra setup needed. `url: https://runapi.ai/mcp
auth: Bearer ${RUNAPI_API_KEY}
`
2. **Prompt the workbench agent** - Ask WorkBuddy to call the RunAPI text_to_image tool with model set to flux-2-pro-text-to-image. Include a prompt, and optionally aspect_ratio (1:1, 4:3, 16:9, etc.) and output_resolution (1k or 2k; Flux 2 Max supports 1k only). For multi-source remixing, tell the agent to use the remix_image tool with source_image_urls instead. `tool: text_to_image · model: flux-2-pro-text-to-image`
3. **Get the result** - The MCP server creates the task, tracks it until completion, and hands the finished image URL back to WorkBuddy. The agent shows the URL in the conversation — no manual polling on your side. `task_id: tsk_abc123 → completed`

## Flux 2 tool parameters

| Parameter | Type | Description |
| --- | --- | --- |
| `model` | `string` | Required. A Flux 2 model ID for the tool, such as flux-2-pro-text-to-image or flux-2-pro-remix-image. The Flux 2 model catalog lists every available version. |
| `prompt` | `string` | Text description of the image to generate. |
| `aspect_ratio` | `string` | Optional. Output aspect ratio: 1:1, 4:3, 3:4, 16:9, 9:16, 3:2, or 2:3. Remix tools also accept auto. |
| `output_resolution` | `string` | Optional. Defaults to 1k. Supported values vary by version; check the Flux 2 model catalog. For Flex and Pro, 2k costs more per image than 1k. |
| `source_image_urls` | `array` | Required for remix_image. Array of source image URLs to blend or transform. |
| `callback_url` | `string` | Optional. Webhook URL for async completion notification. |

## What is Flux 2 on WorkBuddy?

Flux 2 by Black Forest Labs is the production-grade image model that users say "beats Midjourney on photorealism" with material fidelity that actually passes for real photography. It ships with multi-reference conditioning and 4-megapixel output, so you get brand-consistent results without fine-tuning. WorkBuddy reaches it as a tool on the RunAPI MCP server, so a text brief typed into the workbench comes back as a finished image URL.

## Flux 2 use cases

- **E-commerce product photography** - Generate product photos and background swaps that look like real studio shots, replacing manual photography for catalog pages and listings — all requested from a WorkBuddy prompt.
- **Ad localization across markets** - Produce localized ad visuals for 30+ markets from the same prompt structure, swapping text and cultural references while keeping brand consistency.
- **Magazine covers and editorial images** - Create magazine-quality covers with on-image text rendering, where the typography needs to be part of the generated image rather than composited afterward.

## Flux 2 + WorkBuddy questions

### How do the Flux 2 versions differ?

The versions differ in generation speed, output fidelity, and price. Each one exposes text_to_image and remix_image tools on the same RunAPI MCP server. The version table in the Flux 2 model catalog lists every version with its supported parameters and current price.

### Do I need a separate MCP server for Flux 2 image generation?

No. The runapi MCP server you added for chat already exposes Flux 2 and every other RunAPI model as callable tools. The same RUNAPI_API_KEY covers LLM, image, video, and music requests.

### Does Flux 2 output resolution affect pricing?

It depends on the version. Flux 2 Flex and Flux 2 Pro bill per image and cost more at 2k than at 1k. Flux 2 Max outputs 1k only, at a single per-image rate. Check the Flux 2 model catalog or the RunAPI pricing page for current rates.

### How does Flux 2 compare to Flux Kontext?

Flux Kontext specializes in text-guided editing and character consistency with a single input image. Flux 2 focuses on text-to-image generation and multi-source remixing, with several quality versions and selectable output resolution. Both are by Black Forest Labs and available as tools on the same RunAPI MCP server.

### Who handles the async task polling in WorkBuddy?

The RunAPI MCP server does. Flux 2 tasks are async, but the server tracks each task until it completes and returns the finished image URL to WorkBuddy, so you never poll manually from the workbench.


- [WorkBuddy setup guide →](https://runapi.ai/workbuddy.md) - Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
- [Flux 2 models →](https://runapi.ai/models/flux-2.md) - See all Flux 2 variants, pricing, and API docs.

## Try Flux 2 in WorkBuddy today.

Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating images with Flux 2.

[Browse models →](https://runapi.ai/models.md)

---

## More from RunAPI

- [Home](https://runapi.ai/.md)
### Product
- [Model Catalog](https://runapi.ai/models.md)
- [Pricing](https://runapi.ai/pricing.md)
- [Providers](https://runapi.ai/models#all-models)
### Developers
- [Documentation](https://runapi.ai/docs/guides)
- [SDKs](https://runapi.ai/sdk.md)
- [CLI](https://runapi.ai/cli.md)
- [MCP Server](https://runapi.ai/mcp.md)
- [x402](https://runapi.ai/x402.md)
### Guides
- [Claude Code vs Cursor](https://runapi.ai/claude-code-vs-cursor.md)
- [Cursor API Setup](https://runapi.ai/cursor-api-setup.md)
- [RunAPI vs OpenRouter](https://runapi.ai/openrouter-alternative.md)
### Company
- [Enterprise](https://runapi.ai/contact.md)
- [Contact](https://runapi.ai/contact.md)
### Legal
- [Terms](https://runapi.ai/terms.md)
- [Privacy](https://runapi.ai/privacy.md)
- [Site index for agents](https://runapi.ai/llms.txt)

Contact: contact@runapi.ai

## Structured data

```json
[
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "WebSite",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "potentialAction": {
      "@type": "SearchAction",
      "target": {
        "@type": "EntryPoint",
        "urlTemplate": "https://runapi.ai/models?q={search_term_string}"
      },
      "query-input": "required name=search_term_string"
    }
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "Organization",
    "name": "RunAPI",
    "url": "https://runapi.ai/",
    "logo": {
      "@type": "ImageObject",
      "url": "https://runapi.ai/icon.svg"
    },
    "sameAs": [
      "https://github.com/runapi-ai"
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "SoftwareApplication",
    "name": "RunAPI Flux 2 for WorkBuddy",
    "applicationCategory": "DeveloperApplication",
    "description": "Generate images with Flux 2 by Black Forest Labs in WorkBuddy over MCP with RunAPI. Text-to-image and multi-source remix tools, called from the workbench.",
    "url": "https://runapi.ai/workbuddy-flux-2"
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "FAQPage",
    "mainEntity": [
      {
        "@type": "Question",
        "name": "How do the Flux 2 versions differ?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "The versions differ in generation speed, output fidelity, and price. Each one exposes text_to_image and remix_image tools on the same RunAPI MCP server. The version table in the Flux 2 model catalog lists every version with its supported parameters and current price."
        }
      },
      {
        "@type": "Question",
        "name": "Do I need a separate MCP server for Flux 2 image generation?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "No. The runapi MCP server you added for chat already exposes Flux 2 and every other RunAPI model as callable tools. The same RUNAPI_API_KEY covers LLM, image, video, and music requests."
        }
      },
      {
        "@type": "Question",
        "name": "Does Flux 2 output resolution affect pricing?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "It depends on the version. Flux 2 Flex and Flux 2 Pro bill per image and cost more at 2k than at 1k. Flux 2 Max outputs 1k only, at a single per-image rate. Check the Flux 2 model catalog or the RunAPI pricing page for current rates."
        }
      },
      {
        "@type": "Question",
        "name": "How does Flux 2 compare to Flux Kontext?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "Flux Kontext specializes in text-guided editing and character consistency with a single input image. Flux 2 focuses on text-to-image generation and multi-source remixing, with several quality versions and selectable output resolution. Both are by Black Forest Labs and available as tools on the same RunAPI MCP server."
        }
      },
      {
        "@type": "Question",
        "name": "Who handles the async task polling in WorkBuddy?",
        "acceptedAnswer": {
          "@type": "Answer",
          "text": "The RunAPI MCP server does. Flux 2 tasks are async, but the server tracks each task until it completes and returns the finished image URL to WorkBuddy, so you never poll manually from the workbench."
        }
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "HowTo",
    "name": "How to use Flux 2 in WorkBuddy via RunAPI",
    "description": "Add RunAPI as an MCP server in WorkBuddy, prompt the workbench agent to call the Flux 2 text_to_image or remix_image tool, and receive the generated image URL.",
    "step": [
      {
        "@type": "HowToStep",
        "position": 1,
        "name": "Add the RunAPI MCP server",
        "text": "Register an MCP server named runapi in WorkBuddy, pointing at https://runapi.ai/mcp over streamable HTTP, with the Authorization header reading your key from RUNAPI_API_KEY. If RunAPI is already connected for chat, Flux 2 is exposed on the same server — no extra setup needed.",
        "url": "https://runapi.ai/workbuddy-flux-2#how-step-1"
      },
      {
        "@type": "HowToStep",
        "position": 2,
        "name": "Prompt the workbench agent",
        "text": "Ask WorkBuddy to call the RunAPI text_to_image tool with model set to flux-2-pro-text-to-image. Include a prompt, and optionally aspect_ratio (1:1, 4:3, 16:9, etc.) and output_resolution (1k or 2k; Flux 2 Max supports 1k only). For multi-source remixing, tell the agent to use the remix_image tool with source_image_urls instead.",
        "url": "https://runapi.ai/workbuddy-flux-2#how-step-2"
      },
      {
        "@type": "HowToStep",
        "position": 3,
        "name": "Get the result",
        "text": "The MCP server creates the task, tracks it until completion, and hands the finished image URL back to WorkBuddy. The agent shows the URL in the conversation — no manual polling on your side.",
        "url": "https://runapi.ai/workbuddy-flux-2#how-step-3"
      }
    ]
  },
  {
    "@context": "https://schema.org",
    "inLanguage": "en",
    "@type": "BreadcrumbList",
    "itemListElement": [
      {
        "@type": "ListItem",
        "position": 1,
        "name": "Home",
        "item": "https://runapi.ai/"
      },
      {
        "@type": "ListItem",
        "position": 2,
        "name": "RunAPI Flux 2 for WorkBuddy",
        "item": "https://runapi.ai/workbuddy-flux-2"
      }
    ]
  }
]
```
