Skip to content
Tech News
← Back to articles

Using "underdrawings" for accurate text and numbers

read original get Digital Drawing Tablet → more articles
Why This Matters

The 'underdrawings' technique enhances the accuracy of text and numbers in AI-generated images by combining deterministic underlayers with generative models. This approach addresses the limitations of current AI image models in producing precise textual information, which is crucial for applications requiring clarity and correctness. It signifies a significant step toward more reliable AI-generated visuals for industries like gaming, education, and design.

Key Takeaways

I discovered a technique for generating reliable text and numbers in AI generated images.

For example, the following image is considered impossible with state of the art image models. But I made this with Gemini 3.0 Pro (plus one extra step I’m going to explain below).

The Underdrawing Method

I’m totally naming it like it’s a thing but it does seem to be a thing. Here’s a simple a/b test showing the results without and with this method.

Make an image of a game board with 50 stepping stones arranged in a spiral, winding counter-clockwise inward from start at the outside (1) to finish at the centre (50). Each stone is clearly numbered consecutively from 1 to 50. Style: claymation diorama, studio-lit, candy-bright, soft bokeh background.

❌ Gemini 3 Pro (without underdrawing)

As expected. Impressive at first glance but falls apart once you start reading.

❌ ChatGPT Images 2 (without underdrawing)

I was so impressed with ChatGPT-Images-2 release I expected it to get this. Very surprising to see it fail similar to Gemini.

✅ Gemini 3.0 Pro (with the underdrawing method)

... continue reading