14 comments

  • baalimago 3 days ago
    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.

  • qq99 3 days ago
    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

    • rushingcreek 3 days ago
      Thanks, this is good feedback! I'll take a look.
  • john-tells-all 3 days ago
    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.

  • smusamashah 2 days ago
    I clicked on sample prompt. Then had an idea of my own and used that, but page didn't show anything. Now I have used all 2 of my prompts and I can't even go back to see them anymore. There needs to be a history button or something.
  • adi_hn07 2 days ago
    This app is insanely good !! UI/UX is super intuitive and easy to navigate. Ver high quality image generations. The ability to precision edit the generated image makes it the cursor for image generation. Do launch on https://superlaun.ch , would love to have it there :)
  • davidfiala 2 days ago
    I'd love to see more examples in a portfolio or catalogue page. I think it would help me more clearly see what is possible than just the links above. Or at the very least, having them all together on one page without having to open the design chat URL for each to see the examples would be nice.

    I'm glad to see you working on this. It's an incredibly difficult and important space!

  • swyx 3 days ago
    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)

    • rushingcreek 3 days ago
      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.
  • Jonovono 3 days ago
    Nice! I've been playing around with different interfaces for OAI image gen (supports flux and gemini too): https://www.hitslop.com/
    • qq99 3 days ago
      Love the idea of local keys and appreciate your video explaining it! What do you use to record that style of video?
      • Jonovono 3 days ago
        I tried a bunch. The popular one is Screen Studio, but its a crazy subscription price. I made this with Focusee (https://focusee.imobie.com), which from what I can tell has all the features but a one time price!
    • ilaksh 3 days ago
      Its hard for me to get past the name. It's like naming a ceramics manufacturer "punch brittle".
      • Jonovono 3 days ago
        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...

  • captaindiego 3 days ago
    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.
    • rushingcreek 3 days ago
      Founder here. Sorry to hear that. Let me know if you are still getting errors.
    • jaeh 3 days ago
      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.
  • stared 2 days ago
    I guess the name comes from "find", spelled alternatively.

    My initial sense comes from "PhD" (PhD-index?).

  • wwdx 2 days ago
    This needs copy to Figma like google stitch
  • richard___ 3 days ago
    Text editing is the most important part
    • rushingcreek 3 days ago
      The text editing should work well in the chat -- did you have a chance to give it a try?
  • WillAdams 2 days ago
    "Please list the names of all the photographers whose photos of Paul Graham were used in the creation of this training data and image."

    >I’m sorry, but I can’t share details about the specific images or photographers that were part of the model’s training data.

  • infokolya 2 days ago
    [dead]