> For the complete documentation index, see [llms.txt](https://docs.agenticflow.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.agenticflow.ai/reference/nodes/higgsfield_group_image_generation.md).

# Higgsfield: Generate Image

Create images from a prompt, edit reference images, or prepare marketing visuals with the image model you choose.

Find this node under **Higgsfield** in the action picker. It uses a [Higgsfield connection](/integrations/connection-providers/media/higgsfield.md).

## Set up the node

1. Add **Higgsfield: Generate Image** to your workflow.
2. Select your Higgsfield connection.
3. Choose **Model / Action**. The configuration form changes to match your choice.
4. Fill the required fields, using values from earlier steps where needed.
5. Save your changes and run the step. Review its result in **Build** or **History**.

## Parameters and inputs

The fields depend on the selected action. Use the labels, required markers, and available choices shown in your form.

| Input                             | What to provide                                                      |
| --------------------------------- | -------------------------------------------------------------------- |
| Prompt                            | Describe the subject, setting, lighting, and intended use.           |
| Reference images                  | Add images when the selected action supports editing or references.  |
| Style, preset, and image settings | Choose the available style, preset, size, or quality for that model. |

See [model-specific forms](/workflows/media-action-forms.md) for dropdowns, media uploads, repeatable lists, and using earlier results.

## Outputs

Completed images, or a request ID and processing status when generation is still running.

Style and preset choices depend on the selected model. A setting offered by one model may not be available in another.

## Example

Choose **SOUL V2 — Text to image** and describe a ceramic mug on a sunlit kitchen counter. Select the image settings shown in the form, then run the step and review the result.

<details>

<summary>Available Model / Action choices</summary>

* SOUL — Text to image
* SOUL V2 — Text to image
* SOUL Cinema — Text to image
* Marketing Studio Image — 2.0 Alpha
* Marketing Studio Image — 2.5 Flare
* Marketing Studio Image — 2.5 Sunburst
* Grok Image 2.0 — Generate and edit
* Recraft V4.1 — Text to image
* Recraft V4.1 Pro — Text to image
* Recraft V4.1 Utility — Text to image
* Recraft V4.1 Utility Pro — Text to image
* Qwen Image 3 — Text to image
* Qwen Image 3 — Edit images
* Ideogram 4.0 — Generate
* Z-Image Turbo — Generate

</details>

Availability of individual models and resources depends on your provider account. A successful connection does not grant access to every action.

## Related guides

* [Higgsfield connection and action overview](/integrations/connection-providers/media/higgsfield.md)
* [Test a step and reuse earlier results](/workflows/workflow-single-run/run-step.md)
* [Retrieve media and save it to AI Drive](/workflows/workflow-single-run/media-results.md)