<html xmlns:v="urn:schemas-microsoft-com:vml" xmlns:o="urn:schemas-microsoft-com:office:office" xmlns:w="urn:schemas-microsoft-com:office:word" xmlns:m="http://schemas.microsoft.com/office/2004/12/omml" xmlns="http://www.w3.org/TR/REC-html40"><head><meta http-equiv=Content-Type content="text/html; charset=us-ascii"><meta name=Generator content="Microsoft Word 15 (filtered medium)"><style><!--
/* Font Definitions */
@font-face
{font-family:"Cambria Math";
panose-1:2 4 5 3 5 4 6 3 2 4;}
@font-face
{font-family:Aptos;}
/* Style Definitions */
p.MsoNormal, li.MsoNormal, div.MsoNormal
{margin:0in;
font-size:11.0pt;
font-family:"Aptos",sans-serif;
mso-ligatures:standardcontextual;}
span.EmailStyle17
{mso-style-type:personal-compose;
font-family:"Aptos",sans-serif;
color:windowtext;}
.MsoChpDefault
{mso-style-type:export-only;
font-size:11.0pt;}
@page WordSection1
{size:8.5in 11.0in;
margin:1.0in 1.0in 1.0in 1.0in;}
div.WordSection1
{page:WordSection1;}
--></style><!--[if gte mso 9]><xml>
<o:shapedefaults v:ext="edit" spidmax="1026" />
</xml><![endif]--><!--[if gte mso 9]><xml>
<o:shapelayout v:ext="edit">
<o:idmap v:ext="edit" data="1" />
</o:shapelayout></xml><![endif]--></head><body lang=EN-US link="#467886" vlink="#96607D" style='word-wrap:break-word'><div class=WordSection1><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>I have been playing with AI image creation. With the displays in mind that we are talking about on the list. I tried to make some images last night. I asked it to make an image w192 by 80 to fit the Monarch, and one 120 by 80 to fit the Graphiti. I stuck with white and black pixels. Note I know the Monarch is 96 by 40 and the Graphiti is 60 by 40 but I wanted to get a good enough picture of what ever I asked to determine if AI could do this. So, I made it so the picture would have a quarter on the screen at a time. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>The first image I have tried to get ChatGPT to make is the PacMan game . The first thing it returned is an image 760 buy 300 and when I had Jaws look at it, it said it looked like the Packmate game but note it did not make it in the f192 by 80 pixels. I asked it for. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>The second one it made after I told it no, I wanted the entire image to be 192 by 80. Jaws AI told me looked like an abstract view of the old Pacman game. <o:p></o:p></p><p class=MsoNormal>Neither looked good on either tactile display. <o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>I have said all that to ask for those out there that have been playing with making images with AI. Do you have good prompts I could use to make AI draw these images. Maybe what I am asking is not clear enough. I used the following simple prompts to start:<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>“can you take a black and white picture of the Pacman game for a tactile display that has 192 by 80 dots make all lines with one dot width and make it as a downloadable pang”<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>The second prompt I gave it was:<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>“This is 700 by 300 not 192 by 80. Can you make a drawing that is 192 by 80 of the same thing”<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>I won’t send the images here because first I don’t think people want that on the list. If you do want them, send me your email and I will send you the images it made. They are not good on the displays though. Maybe today I will go upstairs and emboss it and see how they look on an embosser.<o:p></o:p></p><p class=MsoNormal><o:p> </o:p></p><p class=MsoNormal>Ken<o:p></o:p></p></div></body></html>