Featured images and diagrams
Generating images, overlaying text, and using reference images (logos, characters)
Featured image
Sorabun automatically generates an image matching the article's title. Under "Settings > Generation defaults > Featured image," you can set:
- Generate automatically by default (
eyecatch_enabled) - Overlay the title text (
eyecatch_text): images with text overlaid tend to get a higher click rate on social media and in listings - Style (
eyecatch_style): flat, photo-realistic, and so on
Diagrams
Sorabun generates and inserts flowcharts, step diagrams, and comparison diagrams based on the body content.
- Number of diagrams (
diagram_count): 0 to 5, or "Let AI decide" - Aspect ratio (
diagram_aspect): 16:9 by default
With "Let AI decide," diagrams are only inserted where the explanation is genuinely complex, so you don't end up with meaningless diagrams.
Image inspection (Pro)
Sorabun shows the generated image to an AI to check for obvious problems (three-fingered hands, extra limbs, garbled text) and regenerates it if it finds any (eyecatch_check, defaults to 1 retry).
If the problem isn't fixed after a retry, it's left as a warning on the job. Treat that as a cue to replace the image yourself.
Note that Sorabun is already instructed to avoid close-ups of hands and fingers, which are prone to these errors. It prioritizes objects, scenery, and symbols over people, and when people do appear, keeps them small and shown from behind.
Using reference images (logos, characters)
You can have your own logo or character appear in generated images.
- Upload the image to the media library
- Specify it in the reference image field under "Settings > Generation defaults" (
eyecatch_ref_ids/diagram_ref_ids) - Choose how it's used
- Always use it: includes it every time
- Leave it to AI: only uses it when it fits the content
Choosing an image generation AI
Under "Settings > Model," you can choose Gemini or OpenAI (GPT Image) separately for featured images and diagrams.
| Gemini | OpenAI | |
|---|---|---|
| Cost | Cheap | Somewhat higher |
| Text rendering | Good | Good |
| Setting key | eyecatch_provider / diagram_provider | Same |
| Model name | image_model, resolution via gemini_image_size | openai_image_model, quality via openai_image_quality |
The key used for image generation may not be set, or you may have specified a model outside your free tier. Check the error details in "Jobs / History."