I've made a Text to image generator and it is not like any others...

Well done on making something more involved and complex 👍

What does "Fegless" mean?

I don't understand asking for a donation because you're down to 512mb of data... how is that related to the generator? What data are you talking about? Why do you want people's email addresses?

Clicking "AI?" just generates whatever the AI feels like. For me it generates some python code for no apparent reason. I'm not sure what that button is meant to be doing, but presumably it's not doing it.

And clicking "AI prompt" puts both the prompt to the text AI and what it returns (the actual image prompt it produces). Which also is presumably not what was intended.

"Import" puts a random actual image prompt in, and doesn't actually "import" anything as far as the user is concerned.

The part of the prompts your page adds have a formatting that doesn't actually help the image generator, but could certainly confuse it. It's written as plain english, with little headings and such, but that's not how image generators use the text. It may have better results if you wrote those prompts in a more image-generator-ish way.

Clicking "random" in the picture settings doesn't change the settings to random things. It just starts a new generation that ignores the prompt entirely, which is unexpected. I don't know what this button is meant to do.

When I go to the page I see an error: "Failed to fetch."

Would be good to have "Random" be an option for picture style/lighting.

Would also be more useful if a randomised setting was picked at random for each generated image, rather than once and then applied to all generations in that set. So that if you generated 4 images with a random location, you'd see 4 random locations for example.

Character background: false, Character personality: false. I don't understand what these mean.

4 comments

https://perchance.org/fegless
Interesting approach. I wanted to try playing with the code, but unfortunately saving a copy to edit doesn't work for me. =/ I just end up with a white screen. I tried pasting the code into a new gen, and that didn't work either. Might be my older browser.
My first feedback is DEAR GOD. I didn't ask for any of the traits of this output. Secondly, the photo presets seem to be generating illustrations.
You've put a lot of work into this and it's cool to be able to customize all the prompts, but man is it hard to get everything in these kinds of generators to work right.
Mostly NSFW image below ::: spoiler spoiler _
:::
Well done on making something more involved and complex 👍
What does "Fegless" mean?
I don't understand asking for a donation because you're down to 512mb of data... how is that related to the generator? What data are you talking about? Why do you want people's email addresses?
Clicking "AI?" just generates whatever the AI feels like. For me it generates some python code for no apparent reason. I'm not sure what that button is meant to be doing, but presumably it's not doing it.
And clicking "AI prompt" puts both the prompt to the text AI and what it returns (the actual image prompt it produces). Which also is presumably not what was intended.
"Import" puts a random actual image prompt in, and doesn't actually "import" anything as far as the user is concerned.
The part of the prompts your page adds have a formatting that doesn't actually help the image generator, but could certainly confuse it. It's written as plain english, with little headings and such, but that's not how image generators use the text. It may have better results if you wrote those prompts in a more image-generator-ish way.
Clicking "random" in the picture settings doesn't change the settings to random things. It just starts a new generation that ignores the prompt entirely, which is unexpected. I don't know what this button is meant to do.
When I go to the page I see an error: "Failed to fetch."
Would be good to have "Random" be an option for picture style/lighting.
Would also be more useful if a randomised setting was picked at random for each generated image, rather than once and then applied to all generations in that set. So that if you generated 4 images with a random location, you'd see 4 random locations for example.
Character background: false, Character personality: false. I don't understand what these mean.