61–70 of 157 posts
This makes me wonder if a future job description will be the equivalent of an AI whisperer. Someone who learns how to prompt AI so well that it becomes their job.
Someone had taken a photo, somehow digitized it, distributed it, and we were looking at a representation good enough that we could tell what it was.
It felt like we were living in the future - me as a middle schooler and him with decades of software development under his belt.
The iPhone maps app with the GPS dot and DALL-E are the only things that have matched that feeling.
I just got access to the DALL-E 2 beta, and it's a ton of fun to make pictures out of everyday occurrences as prompts. Someone else here on HN observed that everyday people don't "get" how huge this all is. I experimented with asking random acquaintances at a local cafe for prompts and showed them the generated pictures. All but one person was totally unimpressed. If everything feels like magic, then what's one more…
I just got access to the DALL-E 2 beta, and it's a ton of fun to make pictures out of everyday occurrences as prompts. Someone else here on HN observed that everyday people don't "get" how huge this all is. I experimented with asking random acquaintances at a local cafe for prompts and showed them the generated pictures. All but one person was totally unimpressed. If everything feels like magic, then what's one more…
Earlier quoted context omitted.
What's the business with Midjourney demanding Discord details to sign up? Seems off.
afaik - the API is exposed as a discord bot, that's how they are managing / restricting access
I’ve spent just over 1 week with DALL•E 2. Over the past 7 days I’ve generated ~1000 images, 150 of which were good enough to save. I only saved images which made me audibly gasp. Witnessing your own novel idea spring to life is a magical experience. DALL•E provides an artistic tool on a comparable level to digital photography, and by extension Photoshop. At this stage it’s 100% clear to me that DALL•E has heralded i…
Honestly, I have a great use case for it currently, but then I realized it can only do square pictures, when I really want something that is much wider than it is tall.
The relevant code is linked below and is a mess, but the idea is: 1. Generate a base image 2. Use inpainting to expand the left-hand side of the root image. You can do this by submitting an image whose left side is transparent and whose right side is the left side of the root image 3. Ditto for right-hand side 4. Stitch the three separate images together https://github.com/charlesjlee/twitter_dalle2_bot/blob/main/...
I am signed up for the waitlist and can't wait to give them my money.
I just got access to the DALL-E 2 beta, and it's a ton of fun to make pictures out of everyday occurrences as prompts. Someone else here on HN observed that everyday people don't "get" how huge this all is. I experimented with asking random acquaintances at a local cafe for prompts and showed them the generated pictures. All but one person was totally unimpressed. If everything feels like magic, then what's one more…
How do you know something is impressive or surprising? You compare it to the previous status of the industry, which is something you know, but the random people in the coffee house don't.
I doubt they really believe it's truly inexplicable. Most layman know that somebody knows what's going on in their device.
And nobody has an explanation for everything they use, but it doesn't mean they get attributed to magic. I have no idea how a bridge is designed and built, but I don't believe it's magic, it's just something beyond my knowledge.
Prompt crafting is quickly becoming an art. I just found out yesterday that there's actually market places for buying and selling prompts [0]. It can really make a big difference if you can tune the image by adding the right words. Midjourney [1] even allows things such as adjusting the weight of each keyword or how "literal" the AI should take your prompt. [0] https://promptbase.com/ [1] https://midjourney.gitbook.i…
Does anyone know what kind of prompt generates such clean, consistent results like these? https://promptbase.com/prompt/clay-emojis https://promptbase.com/prompt/polygon-animals
This makes me wonder if a future job description will be the equivalent of an AI whisperer. Someone who learns how to prompt AI so well that it becomes their job.