Show HN: Phind.design – Image editor & design tool powered by 4o / custom models

14 hours ago (phind.design)

Hi HN,

Today we’re launching phind.design (https://phind.design), an image editor and design tool that uses 4o and custom models to allow users to generate and edit designs for anything from logos and advertisements to creative website and app designs.

4o is great at producing a first version of an image, but is not capable of editing it without messing up other parts of it. We fix this by running Flux Kontext alongside 4o image gen in the chat, as well as by introducing a precision editor powered by custom models where a user indicates an area to modify and we guarantee that only that area will be modified.

Our precision editor is state-of-the-art on image editing in our tests and allows inserting new additional images into the existing image. The latter allows users to insert a logo, product, or face into an image without messing up other parts of the image, and even fix logos and faces that were messed up by 4o. Text editing with the precision edit model is still a work in progress, and we will fix it with the next iteration of that model. We recommend using the chat for editing text for now.

Example: Insert UT Austin logo into helicopter ad (https://phind.design/edit?chat=cmd27o2n10001l704h6865f3u)

We also always produce multiple variations for image generations and edits, as we think this variety is important for getting exactly what you asked for.

Example: Paul Graham in startup heaven (https://phind.design/edit?chat=cmd23h91c000jky04no5d92uy)

One thing we’re excited about is adding more variation into AI-generated websites, as many website builders all use the same CSS libraries, so many websites end up looking the same. We hope to allow builders and creatives to make truly unique designs in 1/10th the time it currently takes with existing tools.

Example: Make me a popeyes landing page where the eyes are actually popping out (https://phind.design/edit?chat=cmd25imtm0001jr046nsag4lu) Example: A train map with sandwich ingredients replacing subway stops. (https://phind.design/edit?chat=cmd23i98c0001ie04l56npyj3)

As engineers who have been frustrated by the time commitment it takes to learn Figma or Photoshop, we hope that phind.design makes it incredibly easy to go from zero to one on your wildest creative ideas.

The editor is far from perfect, particularly when it comes to text. We are working on it and have a new custom precision editing model on the way. In the meantime, we’re excited to hear your comments and feedback!

I have a standardized test I use for testing AI image editors, which I ran on Phind.design as well: I have a close-up picture a keyring which has a small hand-drawn painting of my puppy Freija. So my hand is visible in the image, as I'm holding the keyring. I ask the LLM to extract the puppy from the keyring, enlarge it so it fills the entire image and saturate the colours so that the hand-drawn painitng is the only thing which remains. I'm not interested in the picture of my hand holding a keyring, but the hand-drawn painting of the puppy.

This is somewhat trivial to do in Photoshop/Gimp. Hell, I'm sure most of you can visualize this transformation in your minds even. But it seems to be almost impossible for any AI image editor, Phind.design included.

What I got when I tried this using Phind was the very opposite of what I asked: it kept my hand holding the keyring, the keyring itself, but it replaced the puppy. Perhaps this is user error: should I not select the area I'd like to edit? Regardless, there were no attempts to coach me into using the tool correctly, even though the instructions might have been counter-intuitive, which I'd expect is half the point in using an AI tool.

So, well.. Maybe designers are safe for another day.

One super-easy use case is product size comparison. Example: "hand holding lilygo t3 pro" shows me how big a circuit board and screen is. Product images are everywhere, but it's hard to get a strong idea of how big it really is without a hand or something else in the frame.

First try worked like a charm. Super useful! Thanks.

Cool!

Some feedback: it's too easy to get into a "dead chat".

> Sorry, an error occurred while processing your request.

No way to retry or resubmit or edit anything to get things moving again. Too terminal.

If I just type "try again" (lacking a retry mechanism), having it say "Here is the current image I'm working with" seems unexpected (my follow-up request was going to be for 4 entirely new variations with more specific aspects)

If I go back to the home page and attempt to begin what I imagined is a new chat, it appends this new message onto the previous chat's history. Not sure if that's a visual / caching bug, but it's also jarring

very cool but also i'm struggling with how this relates to the core Phind business? seems a bit out of left field.

(also hi hope you're doing well)

  • hey swyx! hope you’re doing well too. we are exploring some other avenues to the core Phind business and this is one of them. i’m excited by the rate of improvement of the underlying models in this space and it reminds me of the early days of the AI search space when we started working in it in 2021.

Nice! I've been playing around with different interfaces for OAI image gen (supports flux and gemini too): https://www.hitslop.com/

  • Its hard for me to get past the name. It's like naming a ceramics manufacturer "punch brittle".

    • LOL. Long story. But it's actually a word used in react native development. Back in the olden days before ChatGPT I was trying to figure out how to make a button "easier" to press. After digging around for a bit, came across this and I thought the name was so funny. I ended up buying the domain. Had no use for it. Decided to use it for this project as it kinda fit. Press on screen and [ai] slop comes out ;p

      https://reactnative.dev/docs/touchablewithoutfeedback#hitslo...

Can anyone comment if Phind is working again? I was on a pro plan and ended up switching to perplexity because it was unusable for over a week.

  • just send the query multiple times by clicking the question text then pressing enter to resend, usually third time's the charm for me. has been like this for a few weeks, the queries sometimes just error.