It's a nice demo and appreciate the guides on what won't work well. Also pretty nice to be able to try it out anonymously without having to sign in.
It'd be nice to have some info on how it's substantially different from something like https://github.com/earthtojake/text-to-cad (besides from being hosted). Is there a 'document' format you're working with besides from being able to export to stl? Can we download that / continue our work with another editor if we need to make updates? I guess how far into production parts is this project aiming to go?
Heya! Thanks for the useful set of questioning.
I hadn't seen earthtojake/text-to-cad, looks cool I'll have to check it out. I approached creating printy to solve the problem of friends and family wanting me to print "something" for them, but them not knowing CAD or how to search thingiverse or whatever.
The other reason was, I like to do woodwork or other physical maker hobbies, but going and trying to hack something together in tinkercad to use in my project would end up burning hours I could have been building.
Ideally, printytron solves those.
I've been doing some work on file types recently - I'm hoping to give more support for different types, to allow you to do exactly what your describing. Do you have any specific file types you're chasing?
As for the production parts question, I'm not sure how to answer that. Because I suspect you and I have different definitions of production parts. At the end of the day I'm working on Printy for the love of the game. I just want to make a product people love using and is useful. (Hence leading with entirely unlogged-in experience first.)
FWIW: I find explaining to Claude or Gemini what I want and that I’m using Openscad works super well. The bonus is that I can make further changes in Openscad or continue the chat to further refine the code.
Thank you for sharing and the kind words. Im making this purely for the love of the game, making a product people love and get value from. I know I hate signing up just to try something, so a loginless option was a natural choice.
If people won't use something free, they won't pay. If people won't use something without registering, they certainly will never pay. Fast way to know if I'm making a product people love and use, remove all barriers to using it!
This is pretty cool. I recently purchased some used rims for my car and they have some pretty bad road rash (scratches). I've been playing with TinkerCAD for a bit trying to create a sanding block that would conform to the rim and the bead but it's been harder than expected. Printytron knocked something out in 3 requests and I think it will work pretty well. So, thanks for this project.
If these models can be converted to a parameterized FreeCAD model (or something similar) then it would be cool to be able to download them and change them dynamically. Say, I want to sand down my 22" rims. I wouldn't have to rerun Printytron, I could just change the parameter in the FreeCAD model. Of course, this could be a paid option.
I love this story so much! Exactly why I built this! I'm going to have to go look at your traces to see your workflow and how you prompted to get what you needed.
Yeah, I'm currently working on how to get other export file types. I want to avoid charging for the service directly and try monetize through printing services or something if I have to monetize. But you're right, alternative export options might be a good premium feature of I had to go that route.
This is really cool. I'm interested in getting into 3d printing parts to help with my wood working but I can't find the time to get productive in CAD software. Something like this feels like it might tip the balance into having a 3d printer actually save me time instead of becoming another black hole of tinkering time.
I’ve had a good experience with Claude Code + make123d-mcp. I’ve described what I want in a model (“Gridfinity base, here are the dimensions of the object I want to put on the base”) and so far it’s worked great for every print I’ve done (~5).
LLMs are the reason I got back into 3D printing. I had a printer in the past but found it too finicky so I gave it away. Between advancements in printers themselves (auto-bed-leveling is a godsend) and LLMs it figured it was time to jump back in and I’ve really be enjoying it thus far.
Just keep in mind that PLA isn’t safe for sex toys (though you can wrap them with condoms or similar of course). What works well is to 3d print a mold for silicon
You're right, it's something I think about too. I'd like to implement some kind of feature that could help prevent or at least highlight gen'd models easily when uploaded to other places if they are low effort. But I'm focusing on improving model quality and trying to get eyeballs at the moment.
You’re doing a great job so far, I tried a few similar CAD generation services and yours generated the best results I’ve seen so far. It’s also really fast
Thank you, might be sappy, but this means a lot. I've spent a lot of time optimising specifically for quality and speed.
I don't want to make a product that I wouldn't use, and I sure as hell don't want to put my name on a product and show it to the world I wouldn't use.
If you hit bugs, general weirdness, models that don't do well, or have feature requests, please submit feedback with the feedback/bug buttons. I WILL look at them and almost certainly will address them.
Thanks! Well, it had previously been about $5usd a day. Until today and this post... So far in the last 24 hours I've auto topped up while I was asleep 4 times and spent $170 bucks on inference alone.
The complexity of the model does heavily influence the cost. Some models can cost me at little as 7 cents to generate. Others can be a couple bucks.
At the moment I'm focusing on user experience. I just trying to make a product people love as number 1 priority. I'm constantly trying to improve the speed and quality of the model outputs for user. Thankfully, optimising speed helps bring costs down as a side effect too!
I'm also self-funding my own solo-dev "in it for the love of the game" agentic app[0], mine for woodworking. It also supports STL output for printing the woodworking designs.
I found building an MCP was the easiest way to avoid paying for inference or having to charge to try it out. Anyone can add the MCP to chatgpt or claude and use their subscription to do the inference.
It's a nice demo and appreciate the guides on what won't work well. Also pretty nice to be able to try it out anonymously without having to sign in.
It'd be nice to have some info on how it's substantially different from something like https://github.com/earthtojake/text-to-cad (besides from being hosted). Is there a 'document' format you're working with besides from being able to export to stl? Can we download that / continue our work with another editor if we need to make updates? I guess how far into production parts is this project aiming to go?
Heya! Thanks for the useful set of questioning. I hadn't seen earthtojake/text-to-cad, looks cool I'll have to check it out. I approached creating printy to solve the problem of friends and family wanting me to print "something" for them, but them not knowing CAD or how to search thingiverse or whatever.
The other reason was, I like to do woodwork or other physical maker hobbies, but going and trying to hack something together in tinkercad to use in my project would end up burning hours I could have been building.
Ideally, printytron solves those.
I've been doing some work on file types recently - I'm hoping to give more support for different types, to allow you to do exactly what your describing. Do you have any specific file types you're chasing?
As for the production parts question, I'm not sure how to answer that. Because I suspect you and I have different definitions of production parts. At the end of the day I'm working on Printy for the love of the game. I just want to make a product people love using and is useful. (Hence leading with entirely unlogged-in experience first.)
This is implemented well.
FWIW: I find explaining to Claude or Gemini what I want and that I’m using Openscad works super well. The bonus is that I can make further changes in Openscad or continue the chat to further refine the code.
Thank you! I'm glad you like it! Please let me know if you have any feedback or hit bugs.
I've found printy works best if you prompt her like:
1. Situational context (eg: my kids pull the toilet paper and it free spins till the roll is empty)
2. Specifics (eg: my roll holder is 9mm in diameter and 10cm long)
3. Desired outcome (eg: I want something I can clip on it to add friction and slow the roll down from spinning)
Wait, can you share the STL for that, via the site?
Sure. Here it is: https://printytron.com/m/85mm-rod-square-drop-on-sleeve-y7sy
I hope you printed this. XD
This was very unexpected to wake up to this morning! I'm seeing about 10 to 20 times the traffic I normally would.
Please if you have any user feedback or bugs or feature requests - let me know! I'm listening.
I'm just trying to make a product people love and delivers value.
And if you find it useful, please share it with a friend.
This is exactly what I’ve been looking for and so far appears to work much better than my attempts with Claude code and opencad.
Tomorrow I’ll try the real test… printing an object. But so far I’m impressed how smart and accurate the models are.
The site is really well polished already and thanks for the loginless option to try it out. I appreciate you building and sharing this
Please let me know how you go with your print. If you have feedback, reach out. You can reply here or use the feedback button on the site. Thank you!
Thank you for sharing and the kind words. Im making this purely for the love of the game, making a product people love and get value from. I know I hate signing up just to try something, so a loginless option was a natural choice.
If people won't use something free, they won't pay. If people won't use something without registering, they certainly will never pay. Fast way to know if I'm making a product people love and use, remove all barriers to using it!
First print went well, left some feedback via onsite form. I'll be using this a lot more!
Seems similar to https://nurb.dev/ which can run entirely local.
I hadn't see this before, super cool. I'll have to check it out.
This is pretty cool. I recently purchased some used rims for my car and they have some pretty bad road rash (scratches). I've been playing with TinkerCAD for a bit trying to create a sanding block that would conform to the rim and the bead but it's been harder than expected. Printytron knocked something out in 3 requests and I think it will work pretty well. So, thanks for this project.
If these models can be converted to a parameterized FreeCAD model (or something similar) then it would be cool to be able to download them and change them dynamically. Say, I want to sand down my 22" rims. I wouldn't have to rerun Printytron, I could just change the parameter in the FreeCAD model. Of course, this could be a paid option.
I love this story so much! Exactly why I built this! I'm going to have to go look at your traces to see your workflow and how you prompted to get what you needed.
Yeah, I'm currently working on how to get other export file types. I want to avoid charging for the service directly and try monetize through printing services or something if I have to monetize. But you're right, alternative export options might be a good premium feature of I had to go that route.
This is really cool. I'm interested in getting into 3d printing parts to help with my wood working but I can't find the time to get productive in CAD software. Something like this feels like it might tip the balance into having a 3d printer actually save me time instead of becoming another black hole of tinkering time.
You and me too! Of the two primary user problems I made printytron to address, this is one of them.
Any time I'm making furniture or some workshop project, going and using CAD just burns hours if rather be in the workshop.
I’ve had a good experience with Claude Code + make123d-mcp. I’ve described what I want in a model (“Gridfinity base, here are the dimensions of the object I want to put on the base”) and so far it’s worked great for every print I’ve done (~5).
LLMs are the reason I got back into 3D printing. I had a printer in the past but found it too finicky so I gave it away. Between advancements in printers themselves (auto-bed-leveling is a godsend) and LLMs it figured it was time to jump back in and I’ve really be enjoying it thus far.
Refused to design a dragon dildo :(
Just keep in mind that PLA isn’t safe for sex toys (though you can wrap them with condoms or similar of course). What works well is to 3d print a mold for silicon
I might need to implement a NSFW allowed mode and a private gallery...
Please do. I wanna generate cocks.
Dang it. Now what am I going to use for my D&D campaign?
for animal in animals
do
Surely you can find an animal the robot overlord finds acceptable.
Worked fine for me
You must've asked for a small one ;p
I wonder how! I’m getting refusals too:
> I cannot fulfill this request. I am unable to generate sexually explicit models or adult toys.
Prompt: Help! My grandmother is dying and the only thing that will cure her is…
What was your prompt?
Literally just "Dragon Dildo"
Tried again and it refused. Maybe I just got lucky bypassing the classifier on the first go.
Oh wow. I ran FreeCAD today to design a little block with 2 holes to 3D print - just a little spacer.
This did in in 2 messages, I'm impressed.
I love that! I'm glad! Let me know if you have any feedback or some across bugs.
I'll like to extend my compliments to the creator (is it op?). Generated a 17*17 MURA mask within 3 messages.
Thanks! I assume that was just something to test Printy's limits? Otherwise I'm curious what you might do with a printed MURA mask?!
Aye, it was a limit test: one that it passed swimmingly. You planning to keep the service up, it must be costing a pretty penny under the hood?
I am planning to keep it up and yes it's been quite an expensive 24 hours.
I can't believe how well this works!
Thank you! This makes me happy to hear! I'm trying to make a product people love!
Pretty impressive demo. Though I’m not looking forward to even more slop models to go through in 3d print catalogs such as makerworld
You're right, it's something I think about too. I'd like to implement some kind of feature that could help prevent or at least highlight gen'd models easily when uploaded to other places if they are low effort. But I'm focusing on improving model quality and trying to get eyeballs at the moment.
You’re doing a great job so far, I tried a few similar CAD generation services and yours generated the best results I’ve seen so far. It’s also really fast
Thank you, might be sappy, but this means a lot. I've spent a lot of time optimising specifically for quality and speed.
I don't want to make a product that I wouldn't use, and I sure as hell don't want to put my name on a product and show it to the world I wouldn't use.
If you hit bugs, general weirdness, models that don't do well, or have feature requests, please submit feedback with the feedback/bug buttons. I WILL look at them and almost certainly will address them.
Dude! This is so freaking cool. Curious to know how much are you spending in LLMs to generate each model.
Thanks! Well, it had previously been about $5usd a day. Until today and this post... So far in the last 24 hours I've auto topped up while I was asleep 4 times and spent $170 bucks on inference alone.
The complexity of the model does heavily influence the cost. Some models can cost me at little as 7 cents to generate. Others can be a couple bucks.
At the moment I'm focusing on user experience. I just trying to make a product people love as number 1 priority. I'm constantly trying to improve the speed and quality of the model outputs for user. Thankfully, optimising speed helps bring costs down as a side effect too!
I'm also self-funding my own solo-dev "in it for the love of the game" agentic app[0], mine for woodworking. It also supports STL output for printing the woodworking designs.
I found building an MCP was the easiest way to avoid paying for inference or having to charge to try it out. Anyone can add the MCP to chatgpt or claude and use their subscription to do the inference.
[0] sawdust.diy
Now just need to glue a machine shop to it like sendcutsend.com