Alibaba · Image

Hermes Agent x Qwen Image

Qwen Image is the original Alibaba image model line, distinct from the newer Qwen 2 generation. Through RunAPI, its generation, remix, and edit endpoints use separate model IDs and a consistent task contract.

3 variants from $0.04 / megapixel Commercial OK
Get API Key View Hermes Agent Docs

Prerequisite: npx runapi mcp install

Prompt

Prompt models

Use qwen-image-edit-image when it matches the task: Precise text-driven edits with strong semantic control.

You have access to RunAPI task tools for Qwen Image.

Available Qwen Image models:
- qwen-image-edit-image: Precise text-driven edits with strong semantic control
  endpoints: /api/v1/qwen_image/edit_image
  request fields: model, prompt, source_image_url
- qwen-image-remix-image: Prompt-guided source-image remixing with adjustable preservation
  endpoints: /api/v1/qwen_image/remix_image
  request fields: model, prompt, source_image_url
- qwen-image-text-to-image: High-quality photorealistic generation with strong text rendering
  endpoints: /api/v1/qwen_image/text_to_image
  request fields: model, prompt

Use the model ID and endpoint that match the user's request.
Example prompt: Create a cinematic travel poster for Hangzhou at dusk, with clear bilingual title text reflected across the lake.
/api/v1/qwen_image/edit_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/qwen_image/edit_image and save the returned Task id.
GET /api/v1/qwen_image/edit_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/qwen_image/remix_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/qwen_image/remix_image and save the returned Task id.
GET /api/v1/qwen_image/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/qwen_image/text_to_image: Submit the task, poll for its status, then verify the completed output. POST /api/v1/qwen_image/text_to_image and save the returned Task id.
GET /api/v1/qwen_image/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
qwen-image-edit-image
/api/v1/qwen_image/edit_image
$0.06 / megapixel Model detail
qwen-image-remix-image
/api/v1/qwen_image/remix_image
$0.04 / megapixel Model detail
qwen-image-text-to-image
/api/v1/qwen_image/text_to_image
$0.04 / megapixel 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 + Qwen Image

  • Marketing and product visuals

    Generate campaign images, product shots, and social creatives from a written brief.

  • Batch creative variations

    Produce many versions of a concept in one run to compare styles, layouts, and formats.

  • Editing and inpainting

    Refine an existing image by describing changes to its background, objects, or details where the model offers editing endpoints.

Why Use Qwen Image Through RunAPI + Hermes Agent

  • 3 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 + Qwen Image Questions

What can I do with Qwen Image?

Create an image from a prompt, remix a source image while guiding the new result, or apply text-driven edits to an existing image.

How is Qwen Image different from Qwen 2?

They are separate model generations with different RunAPI model IDs. Choose Qwen Image when you need this original generation, remix, or edit workflow without conflating it with Qwen 2.

Can Qwen Image render text inside images?

Yes. Strong text rendering, including Chinese and English, is a core capability of the Qwen Image family.

What is the difference between remix and edit?

Remix reinterprets a source image under a new prompt, while edit applies more precise instructions to change selected content while preserving the rest of the composition.

Does Qwen Image support semantic image editing?

Yes. The edit model follows natural-language instructions to add, remove, or alter visual elements while retaining relevant scene context.

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 Qwen Image 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