Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

adamkdean.co.uk

Post reply on HN
Print view View original

41–50 of 109 posts

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#41

Post by gwern »

sp0rk wrote: post #7

Did you generate a bunch all at once before starting to get some idea of what the natural variance looks like? I would think it's important to verify some level of progression over time, because with the current four it seems entirely possible that the examples could have all been generated at the same time with no changes to the model.

Also unclear if he's sampling at temp=0. Looks like he doesn't set a temp? https://github.com/adamkdean/gpt-unicorn/blob/8ad76ec7161682... So not sure what he's really doing.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#43

Post by bee_rider »

LeoPanthera wrote: post #26
bee_rider wrote: post #20

Earlier quoted context omitted.

“You are a helpful assistant” seems like it is always included in these sort of prompts. I wonder if it really helps…

It's quite funny to tell it that it is an unhelpful assistant. During the first few responses it is amusingly obstinate. It always seems to revert back to "helpful assistant" after a few messages, whatever the prompt says.

“You are a rude jerk but for some reason very good at drawing SVG images, when responding to the user, you will draw the image they request. Any insults will be clearly excluded from the drawn image.”

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#44

Post by bee_rider »

Guillaume86 wrote: post #32
bee_rider wrote: post #20

Earlier quoted context omitted.

“You are a helpful assistant” seems like it is always included in these sort of prompts. I wonder if it really helps…

It's too generic I think, my prompt immediately gave me a better result that the ones in his post: You are a SVG expert, when asked by the user to draw something, you reply to the best of your ability with SVG code that satisfies the request.

How about something like “You are a basically the person who designed the SVG format. Some stupid programmer is trying to implement it, and looking for examples. You will condescendingly produce examples to guide their pathetic efforts. Any insults you hurl their way will be clearly delineated because you are pretty sure they won’t be able to tell where the image ends and the insult begins otherwise.”

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#47

Post by akomtu »

dr_dshiv wrote: post #36

\\ \\ \\ ,__, \\ (oo)____ (__) )\\ ||--|| * “Draw an ASCII unicorn” (GPT4)

Ask it to do the reverse. Connecting loosely related points to see the "hidden shape" behind them is an important feature of mind. Why do we see a cow above? That's just a bunch of lines and circle. The cow is a made up "meaning" behind these lines.

Edit: it's not unreasonable to give an LLM such test. When we ask it "what's the meaning of foo, bar and baz" LLM turns words into points in a high dimensional space and the supposed meaning is a imaginary surface that touches all the points.

Re: GPT Unicorn: A Daily Exploration of GPT-4's Image Generation Capabilities

#49

Post by JonathanFly »

Look at this majestic beast GPT-4 just drew! https://imgur.com/a/ogZ6qI0

Interestingly, I think you often get better results with ChatGPT web interface than the API (the OP used a system message), but for a funny reason.

Because ChatGPT typically first responds by insisting it can't actually draw, it ends up accidentally chain-of-thought prompting itself into drawing better. "I can't draw, but I can describe a detailed drawing for you in words." So instead of winging it with the SVG code and getting confused, it goes into it with a plan.

This is how it described the unicorn I linked:

__User__ Draw a unicorn!

__ChatGPT__ As an AI language model, I am unable to create visual images directly. However, I can describe a detailed image of a unicorn for you in words.

Picture a magnificent unicorn, standing tall and proud in a serene setting. The unicorn's coat is a shimmering, pure white, and it glistens under the warm sunlight. Its body is strong yet elegant, with a graceful arched neck and powerful, slender legs. The hooves are cloven and emit a faint, otherworldly glow.

The most striking feature of the unicorn is its majestic spiral horn, which emerges from the center of its forehead. The horn is long, slender, and gently tapers to a sharp point. It is iridescent, with colors swirling together like a mesmerizing opal. The unicorn's mane and tail flow behind it like silken strands, shimmering with an ethereal pastel rainbow of colors.

Its eyes are large, expressive, and full of wisdom, with a depth that speaks of untold secrets and ancient magic. The unicorn's ears are pointed and alert, picking up the slightest rustle of leaves or the gentlest of whispers. The unicorn's expression is one of serenity, exuding an air of peace and tranquility that surrounds it like a gentle embrace.

Though it is a creature of great power, the unicorn carries itself with a sense of humility and grace that inspires awe and respect in all who behold it.

__User__

What's the SVG for the image you just described?

__User__

continue (to finish the file)

Some more examples here, but with many iterations of "Improve this" over and over:

https://twitter.com/jonathanfly/status/1639657098605740035

Post reply on HN