When you submit an image prompt to Gemini Google is taking your prompt and running it through their language model on the backend before it is submitted to the image model.
The language model has a set of rules where it is specifically told to edit the prompt you provide to include diversity and various other things that Google wants injected in your prompt.
The language model takes your prompt, runs it through these set of rules, and then sends the newly generated woke prompt (which you cannot access or see) to the image generator.
Left alone without this process, the image model would generate expected outcomes for these prompts. Google has to literally put words in your mouth by secretly changing your prompt before it is submitted to the image generator.
How do I know this? Because we've built our own image AI at Gab here: http://gab.ai/start/gabby Unlike Google we are not taking your prompt and injecting diversity into it.
[ + ] Fascinus
[ - ] Fascinus 3 points 1.2 yearsFeb 22, 2024 21:41:16 ago (+3/-0)
https://files.catbox.moe/mxkjjj.jpeg
https://files.catbox.moe/7hvwds.jpeg
https://files.catbox.moe/pmopoo.jpeg
https://files.catbox.moe/mzwqiq.jpeg
https://files.catbox.moe/w8bx90.jpeg
Alternate links:
https://pomf2.lain.la/f/eowhojpc.jpeg
https://pomf2.lain.la/f/as9kzwky.jpeg
https://pomf2.lain.la/f/ourd0gls.jpeg
https://pomf2.lain.la/f/by9u9dro.jpeg
https://pomf2.lain.la/f/s192ugpd.jpeg
https://i.ibb.co/GvC3P6t/GG6-BL5-QXc-AAGm2-H.jpg
https://i.ibb.co/0GZ0ddc/GG3i-B64-XAAAlj-Kk.jpg
https://i.ibb.co/WpPd5cP/GG3i-Cit-Xs-AEr4-P3.jpg
https://i.ibb.co/HKNb593/GG3i-EL0-XEAAS99v.jpg
https://i.ibb.co/gz6X3JG/GG3i-FVKWs-AE0m8-E.jpg
https://qu.ax/jxPJ.jpeg
https://qu.ax/zJUq.jpeg
https://qu.ax/DTem.jpeg
https://qu.ax/bJxe.jpeg
https://qu.ax/OwEc.jpeg
When you submit an image prompt to Gemini Google is taking your prompt and running it through their language model on the backend before it is submitted to the image model.
The language model has a set of rules where it is specifically told to edit the prompt you provide to include diversity and various other things that Google wants injected in your prompt.
The language model takes your prompt, runs it through these set of rules, and then sends the newly generated woke prompt (which you cannot access or see) to the image generator.
Left alone without this process, the image model would generate expected outcomes for these prompts. Google has to literally put words in your mouth by secretly changing your prompt before it is submitted to the image generator.
How do I know this? Because we've built our own image AI at Gab here: http://gab.ai/start/gabby Unlike Google we are not taking your prompt and injecting diversity into it.
[ + ] HonkyMcNiggerSpic
[ - ] HonkyMcNiggerSpic 1 point 1.2 yearsFeb 22, 2024 22:55:52 ago (+1/-0)
[ + ] boekanier
[ - ] boekanier 0 points 1.2 yearsFeb 23, 2024 01:23:20 ago (+0/-0)*
[ + ] Zyklonbeekeeper
[ - ] Zyklonbeekeeper 0 points 1.2 yearsFeb 22, 2024 23:22:26 ago (+0/-0)