Signage / text control

Hello! Is there a way to keep Veras from turning my prompts into signs/labels?

Conversely, can I get Veras to do this on purpose (but tell it which words I wanted it to try to put on there)?

it also uses the prompts to make graphic/text overlay (this was an accidental rendering of a plan that was kind of interesting!)

1 Like

I made a quick test model to further explore this.

I was able to make part of the text become signage, by adding ((architecture sign)) to the prompt:
exterior shot of utopian architecture building, ((architecture sign))

To fix part of the prompt being interpreted as signage, you can use the Render Selection tool. Select the region to change, update the prompt and render. You can optionally turn on the seed to match the original render to try to preserve a better blend.

2024-05-08 - 09-09-41 - Veedub64

The blend can also be improved with the Render Selection Blend button:

2024-05-08 - 09-16-36 - Veedub64

For the text graphic - Veras uses the base image as input. Here’s a post that expands on how it works, and how it will change in the future: Questions for Better Result