> For the complete documentation index, see [llms.txt](https://docs.3techagency.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.3techagency.com/help-center/workflows-and-recovery/image-generation-fails.md).

# Image generation fails

Fix missing image models, timeouts, drawings instead of photos and rejected uploads.

Open **WP AI Manager > Settings > AI Models** first. **Image models** shows the models tried, in order. **Last image problem** shows the time, model, error code and message; **Technical detail** shows what the uploader received and which plugins hooked into uploads.

| Message                                                       | Cause                                                      | Fix                                                                                      |
| ------------------------------------------------------------- | ---------------------------------------------------------- | ---------------------------------------------------------------------------------------- |
| None of your connected providers can make images              | No image-capable connector                                 | Connect one (for example OpenAI or Google) in **Settings > Connectors**                  |
| did not answer within 150 seconds                             | The provider was slow                                      | Ask for fewer images at once, or retry later                                             |
| The image model X returned a drawing (SVG) instead of a photo | The only connected image model draws                       | Connect a photo model: gpt-image, DALL-E, Imagen, Gemini image, Flux or Stable Diffusion |
| This SVG file could not be sanitized (on a .png)              | Kirki's upload check mistook a photo for SVG               | Update to 1.3.0, which steps around SVG-only checks for confirmed photos                 |
| Images stop partway                                           | A call stops after about 75 seconds and saves what is done | Let the assistant continue; it adds the rest to the gallery                              |

The assistant never uploads an SVG or HTML drawing in place of a generated image. Each saved image and each attach step can be undone in **History**.

See [Generate images](https://docs.3techagency.com/documentation/workflows/generate-images).


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.3techagency.com/help-center/workflows-and-recovery/image-generation-fails.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.