This seems to imply that the capabilities being tested are like the descriptive words used in the prompts, but, as a category using random words would be just as valid for exercising the extents of the underlying math. And when I think of that reality I wonder why a list of tests like this should be interesting and to what ends. The repeated nature of the iteration implies that some control or better quality is being sought but the mechanism of exploration is just trial and error and not informative of what would be repeatable success for anyone else in any other circumstance given these discoveries.
Is it me or ChatGPT change subtle or sometimes more prominent things? Like ball holding position of the hand, face features like for head, background trees and alike?
Using gen. ai for filters is stupid, a filter guarantees the same object but filtered, a gen. AI version of this guarantees nothing and an expensive AI bill.
It’s like using gen. ai to do math instead of extracting the numbers from a story and just doing the math with +, -, / and *
It was interesting to see how often the OpenAI model changed the face of the child. Often the other two models wouldn't, but OpenAI would alter the structure of their head (making it rounder), eyes (making them rounder), or altering the position and facing of the children in the background.
It's like OpenAI is reducing to some sort of median face a little on all of these, whereas the other two models seemed to reproduce the face.
For some things, exactly reproducing the face is a problem -- for example in making them a glass etching, Gemini seemed unwilling to give up the specific details of the child's face, even though that would make sense in that context.
It's interesting to me that the models often have their "quirks". GPT has the orange tint, but it also is much worse at being consistent with details. Gemini has a problem where it often returns the image unchanged or almost unchanged, to the point where I gave up on using it for editing anything. Not sure if Seedream has a similar defining "feature".
They noted the Gemini issue too:
> Especially with photos of people, Gemini seems to refuse to apply any edits at all
I like that they call openai’s image generator ground breaking and then explain that it’s prone to taking eight times longer to generate an image before showing it add a third cat over and over and over again
Found OpenAI too often heavy handed. On balance, I'd probably pick Gemini narrowly over Seedream and just learn that sometimes Gemini needs a more specific prompt.
I came to the same conclusion as the authors after generating 1000s of thumbnails[1]. OpenAI alters faces too much and smoothes out details by default. NanoBanana is the best but lacks high fidelity option. SeeDream is catching up to NanoBanana and sometimes is better. It's been too long since OpenAI's gpt-img-1 came out, hope they launch a better model soon.
Hey. We'd love to fund thr generations for free for you to try Riverflow 2 out if you're up for it. Riverflow 1 ranks above them all and 2 is now in preview this week.
The shortcut to flip between models in an expanded view is nice, but the original image should also be included as one of the things to flip between, and should be included in the side by side view.
I dunno about you lot, but I actually really like Stable Diffusion 1.5.
I like giving it weird, non-prompts, like lines from songs or novels. I then run it for a few hundred generations locally and doing stuff with the malformed shit it comes out with. I have a few art projects like this.
Timings were measured on a consumer internet connection in Japan (Fiber connection, 10 Gbps nominal bandwidth) during a limited test run in a short time period.
"consumer internet connection in Japan", "10 Gbps nominal bandwidth"
Coming from a third world country, that surprises me.
The 10gbit connection costs me ¥5,000/mo (around USD 30/mo), which was actually slightly cheaper than I was paying for 1 Gbit...
The main issue is latency and bandwidth across the oceans since Asia far away from the US where a lot of servers live, and even for services that are distributed, I live in a rural prefectural capitol of Japan 1000 km away from Tokyo where all the "Japan" data centers are, so my ping is always unimpressive despite the bandwidth.
33 comments
[ 3.6 ms ] story [ 42.0 ms ] threadLove the optimism
It’s like using gen. ai to do math instead of extracting the numbers from a story and just doing the math with +, -, / and *
It's like OpenAI is reducing to some sort of median face a little on all of these, whereas the other two models seemed to reproduce the face.
For some things, exactly reproducing the face is a problem -- for example in making them a glass etching, Gemini seemed unwilling to give up the specific details of the child's face, even though that would make sense in that context.
They noted the Gemini issue too:
> Especially with photos of people, Gemini seems to refuse to apply any edits at all
[1] = https://thumbnail.ai/
I like giving it weird, non-prompts, like lines from songs or novels. I then run it for a few hundred generations locally and doing stuff with the malformed shit it comes out with. I have a few art projects like this.
Aphex Twin vibes.
"consumer internet connection in Japan", "10 Gbps nominal bandwidth"
Coming from a third world country, that surprises me.
The main issue is latency and bandwidth across the oceans since Asia far away from the US where a lot of servers live, and even for services that are distributed, I live in a rural prefectural capitol of Japan 1000 km away from Tokyo where all the "Japan" data centers are, so my ping is always unimpressive despite the bandwidth.