cartertemm wrote:zakc93 wrote:@cartertemm,
Would you consider adding an option to type in a prompt upon triggering one of the options? Sometimes you encounter an image that you want to know something specific about, and it would be easier to do that than edit the default prompt each time. The simplest might be a checkbox in the settings that when checked will bring up a TextEntryDialog with the default prompt whenever an image description is done.
Totally, you are actually spot on with the implementation I have planned. Except there will also be a list of saved prompts. I've noticed that most people seem to cycle through instruction sets depending on the task at hand i.e. recording a professional quality video will demand different feedback from attempting to deduce what an inaccessible button does, so the goal is to make it as straightforward as possible to toggle between them.
Another thing I've noticed is that while some of us really enjoy prompt engineering for the sake of seeing what we can squeeze out of the different models, the vast majority of this addons users just want something that works. I think there would be immense value in a repository of good prompts for different tasks broken down by model and maintained by contributions from the community. Along with demonstrating what is all possible it would be good to document what works and where, so people aren't expected to pay for a model that may not be optimal for their primary case. I have a couple describe selfie prompts that work spectacularly in Be My AI and Claud, but Gemini completely chokes on the one I use for comics. They're interesting like that.
In regards to this implementation, I thought something that could be pretty neat would be some sort of way to cycle between prompts like how you can choose different speech synthesis settings on NVDA. E.g, holding down the NVDA key, another key, and using the arrow keys to switch between prompt profiles.
The example I thought of was, say, you're playing a video game, and you have a prompt specifically for navigation, and one for reading the interface. You label them "Navigation", and "GUI". And you could swap between the two modes quickly that way. There could be maybe like three different presets for each model?
Not sure, this is one way I thought could work pretty well.