311–320 of 629 posts
Earlier quoted context omitted.
That is an unexpectedly literal definition of "full glass".
That's the point. With the old models they all failed to produce a wine glass that is completley to the brim full. Because you can't find that a lot in the data they used for training.
OpenAI's livestream of GPT-4o Image Generation shows that it is slowwwwwwwwww (maybe 30 seconds per image, which Sam Altman had to spin "it's slow but the generated images are worth it"). Instead of using a diffusion approach, it appears to be generating the image tokens and decoding them akin to the original DALL-E ( https://openai.com/index/dall-e/ ), which allows for streaming partial generations from top to botto…
As a user, images feel slightly slower but comparable to the previous generation. Given the significant quality improvement, it's a fair trade-off. Overall, it feels snappy, and the value justifies a higher price.
Earlier quoted context omitted.
Is that an artifact of the training data? Where are all these original images with that cartoony look that it was trained on?
Ever since Midjourney popularized it, image generation models are often posttrained on more "aesthetic" subsets of images to give them a more fantasy look. It also help obscure some of the imperfections of the AI.
What's important about this new type of image generation that's happening with tokens rather than with diffusion, is that this is effectively reasoning in pixel space. Example: Ask it to draw a notepad with an empty tic-tac-toe, then tell it to make the first move, then you make a move, and so on. You can also do very impressive information-conserving translations, such as changing the drawing style, but also stuff l…
Hmmm, I wanted to do that tic tac toe example, and it failed to create a 3x3 grid, instead creating a 5x5 (?) grid with two first moves marked. https://chatgpt.com/share/67e32d47-eac0-8011-9118-51b81756ec...
For a start the image is wrong, and also I know I can make more requests, because that what tools are for. Its like a passive aggressive suggestion that I made the AI go out of its way to do me a favor.
Earlier quoted context omitted.
> What's important about this new type of image generation that's happening with tokens rather than with diffusion That sounds really interesting. Are there any write-ups how exactly this works?
There are a few different approaches. Meta documents at least one approach quite well in one of their llama papers. The general gist is that you have some kind of adapter layers/model that can take an image and encode it into tokens. You then train the model on a dataset that has interleaved text and images. Could be webpages, where images occur in-between blocks of text, chat logs where people send text messages and…
Is it live yet? Have been trying it out and am still getting poor results on text generation.
So far it seems to be the same for me. It seems like an odd way to name/announce it, there's nothing obvious to distinguish it from what was already there (i.e. 4o making images) so I have no idea if there is a UI change to look for, or just keep trying stuff until it seems better?
Has the meaning of the words "available today" changed since I learned them?