Claude visitors: new accounts receive $1.00 in bonus API credit within 30 days. One per person; usage credits only.
Use Flux Kontext in WorkBuddy.
Flux Kontext by Black Forest Labs handles text-guided image editing and generation with character consistency. WorkBuddy calls it through the RunAPI MCP server — describe the image or the edit in a prompt, and the workbench agent returns the finished image URL.
Use the runapi MCP server to generate an image with Flux Kontext Pro.
Requirements:
- Call the RunAPI text_to_image tool with model "flux-kontext-pro"
- Prompt: a matte-black water bottle on a beige stone surface, soft side light, studio photography
- Wait for the task to complete and show me the image URL
{
"mcpServers": {
"runapi": {
"url": "https://runapi.ai/mcp",
"transport": "streamable_http",
"headers": {
"Authorization": "Bearer ${RUNAPI_API_KEY}"
}
}
}
}
{
"task_id": "tsk_abc123",
"status": "completed",
"model": "flux-kontext-pro",
"output": {
"image_url": "https://media.runapi.ai/outputs/tsk_abc123.png"
}
}
Use Flux Kontext in WorkBuddy in three steps
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 you already connected RunAPI for chat, Flux Kontext is exposed on the same server — no extra setup needed.
url: https://runapi.ai/mcp
auth: Bearer ${RUNAPI_API_KEY}
Prompt the workbench agent
Ask WorkBuddy to call the RunAPI text_to_image tool with model set to flux-kontext-pro. Describe the image you want, or pass an image_url plus an editing instruction for in-context editing.
tool: text_to_image · model: flux-kontext-pro
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 Kontext tool parameters
| Parameter | Type | Description |
|---|---|---|
model |
string |
Required. flux-kontext-pro or flux-kontext-max. |
prompt |
string |
Text instruction for generation or editing. |
image_url |
string |
Source image URL for in-context editing. |
aspect_ratio |
string |
Optional. Output aspect ratio. |
What is Flux Kontext on WorkBuddy?
Flux Kontext by Black Forest Labs is a continuous image editing model that users say is "better than ChatGPT and Gemini" for precise modifications. You describe what to change in plain text, and it modifies that part while keeping everything else intact — the face stays the same when you swap an outfit, the product stays in position when you replace the background. WorkBuddy reaches it as a tool on the RunAPI MCP server, so edits happen right inside the workbench.
Flux Kontext use cases
Background replacement while keeping subjects
Swap product or portrait backgrounds while the subject stays in the exact same position — no masking, no inpainting, just a text instruction typed into WorkBuddy.
Clothing and appearance changes
Change outfits, hair color, or accessories on a character while preserving facial identity, useful for fashion mockups and character design iteration.
Text replacement on signs and labels
Replace text on signs, product labels, or storefronts in existing images — type the new text in the prompt and Flux Kontext renders it in place.
Flux Kontext + WorkBuddy questions
Yes. Add RunAPI as an MCP server in WorkBuddy, then ask the agent to call the text_to_image tool with model set to flux-kontext-pro. The same RUNAPI_API_KEY you use for chat handles image generation.
No. The same RUNAPI_API_KEY works for all RunAPI models — LLM, image, video, and music. One MCP server, one key, one billing account.
The RunAPI MCP server does. Flux Kontext 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.
Flux Kontext Pro starts at 5 cents per image. Flux Kontext Max costs more for higher fidelity. Check the RunAPI pricing page for current rates — billing is pay-as-you-go with no subscription.
Yes. Pass the original image as image_url and write something like "change the sign text to OPEN" in the prompt. The model renders the new text in the same position and style as the original, which works well for label and storefront mockups.
WorkBuddy general setup
Not connected yet? Start with the RunAPI MCP setup guide for WorkBuddy.
WorkBuddy setup guide →Flux Kontext model catalog
See all Flux Kontext variants, pricing, and API docs.
Flux Kontext models →Try Flux Kontext in WorkBuddy today.
Get a free RunAPI key, add the MCP server to WorkBuddy, and start generating and editing images with Flux Kontext.