maalber

Curious about your main motivation to build this. What sets this apart from Miro you think?

Haha, interesting! What made you stop?

I might get back to you regarding the domain

Fair point, I gathered the crowdsourcing element to be implicit but I included it for completeness. The novelty here is the direct interface to LLMs.

I thought OpenAI had been sleeping a bit and given up on the image generation race. However, with the recent release of the oddly named 4o Image Generation model (Why not continue with the DALL-E naming scheme? I personally love the pun) it looks like they cooked up one hell of a model.

If you are into visual GenAI you have probably already seen many examples of quite incredible outputs from the new model. However, we decided that we wanted to make a large scale evaluation, based on 200k human responses across 13k image pairings.

Unfortunately that also meant that we had to generate a large amount of new images, and since OpenAI have not yet opened up API access, we had to do it manually through the UI :(.

The benchmark tests the model in coherence, prompt-alignment, and overall aesthetic preference. Especially for the first two, OpenAI's new model is very far ahead of the competition.

Check out the detailed results and the collected data which is openly available on huggingface!

Let me know if you have questions or feedback!

Can definitely relate to the feeling of getting buried on producthunt! Nice work on this, might just have to try it out.

Cool! Did not know about this. I was not able to see anything other than the pipe - which I assume is the SDR versions, maybe some clearer instructions/limitations (and description of what you should expect to see) would be beneficial.

Can you provide some context or additional info?

Looks nice. What do you do to fetch the job postings?

Looks like currently you only support jobs in the US, is that correct?

Why does it show Chinese characters in the tab title once the countdown starts? Is this intended? 番茄工作法

Pretty cool! And also really difficult as it turns out. Love that you can try it without signing up! Runs quite smooth and I like the simplicity of the UI. Maybe a button to return to the starting position is missing?

Call me old fashioned, but I think a speech should be something personal that reflects you and the person/people on the receiving end of the speech. If you do not know what to say, then maybe there is no need for a speech. That being said, it could be helpful to some people that have something particular things on their mind, but unsure how to structure it into a speech.

Nice job on finishing this project though!

Looks cool!

Did not really manage to get very far yet, but maybe I will revisit later. I was very confused by frequently going to that landing page, which is still WIP, but I guess it will make more sense to me if I spend some more time. In general I was missing a bit of intro, but I assume that is part of the experience

Checked it out quickly, looks cute and inviting.

Is there a reason you did not submit the thread with the link? I was a little bit confused that the title did not take me to the link and I think most HN users would expect that as well - just a pointer :)

Sounds really cool, but i agree with the previous comment that some example would be a very cool, as cloning and running the repo is a bit cumbersome to quickly check it out.

Can you elaborate a bit on the technical details?

What sets this apart from a lot of the similar tools out there?

Do you train your own AI or use off-the-shelf stuff? Do you use an image generator that you convert to SVG or do you output SVGs directly?

Cool idea, simple interface.

What are your hopes with this? Is it just for yourself to use, or do you hope to get a large gallery of submissions? I was hoping I could submit to the gallery without logging in, but in retrospect I do see why that probably should not be allowed

Can you elaborate on the technical details? Have you trained your own model? Or using something off the shelf?

What was your motivation for creating this?

I agree that in my experience, AI image generation does generally still struggle a lot with generating nice simplistic graphics relevant for these types of uses. However, I think the idea of having a large enough catalogue of graphics, pictograms, and backgrounds that an "AI" could choose from based on the instructions would give a much more customized experience.

Cool! Maybe it would be nice to see the software that it is an alternative to directly on the card as well?

Also, how do you qualify whether a solution is an alternative? How much of a 'drop-in replacement' should it be?

I like the idea of a design tool that helps making nice looking infographics. Initially I assumed that the graphics would also be generated, or at least be looked up in a relatively extensive database. However, it appears that the template dictates the layout and the only thing that is really generated is the text, which imo does not warrant a specific tool. In the end, I think this tool is a little misleading currently and could be a lot more than what it currently is

Wow, manually reviewing 50k photos is a lot! Would you be willing to share what the cost of that was?

Love the idea about a demo on twitch. Simple yet effective! Next up, develop a twitch bot interface so you can handle everything directly there

Interesting idea and execution! So basically you wanted to find hotels where the rooms have office chairs and a desk? Or just in any of the images, e.g., a lobby?

Side note; I love how YOLO, a deep learning based model, is now being referred to as traditional object detection. Template matching gang rise up.

I constantly run out of space and the endless cycle of cleaning out a few images continues every few weeks/months. This actually seems very interesting. I was not aware that this was already a crowded market, but it makes sense I suppose. I think the transparency and privacy points that you highlight are very key, however it does not seem to be very clearly highlighted on the actual app page or your landing page. Is there a reason for this?

Very nifty idea! And cute, simple visuals

What am I looking at? Maybe I am missing some contexts

What was the motivation for this?

The typo is rather brutal, at least since i usually make several typos at once :D

Can you elaborate on the tech behind? In which way do you use AI? This seems like a 'regular' optimization problem to me.