I am currently building an AI product which relies on Imagen 3 to generate a lot of photorealistic, cinematic or HDR images. I tried Imagen 4 during preview, but results were too "cartoonish". Did anyone else have the same experience?
Clicking on "Read the documentation" leads to a page that documents nothing about the latest Imagen models and only provides examples using Gemini 2.0 Flash.
I guess it's kinda nicely genuine that the "four panel comic strip" has some errors in it (misunderstanding caption + cat high-fiving itself in the bonus fifth panel)
The webcomics is awful. It feels off, the characters look very fake, unsettling in the way they communicate. The prompt is shown bellow the image, but for me the result looks closer to a prompt "Create lifeless characters reciting marketing slop. They must fake an over exaggerated excitement but it should be clear they don't believe in what they're saying and have no souls".
Also, the prompt specifically ask "Panel 4 should show the cat and dog high-fiving" but the cat is high-fiving ... the cat. Personally I find this hallucinated plot twist good, it makes the ending a bit better. Although technically this is demonstrating a failure of the tool to follow the instructions from the prompt. Interesting choice of example for an official announcement.
The comments here are priceless. In less than five years time we have gone from "That's impossible" to "Meh, it doesn't solve P=NP if prompted.".
For those commenting in the latter category, it might be worthwhile to read a bit about the underlying technology and share your insights on why it does not deliver.
>The model may output text only. Try asking for image outputs explicitly (e.g. "generate an image", "provide images as you go along", "update the image").
>The model may stop generating partway through. Try again or try a different prompt.
I have found Imagein to be a good general purpose editor and we use it to clean up bitmaps, and adjust black points and white points and curves on greyscale, so it is good for preparing B&W greyscale photographs for print to compensate for dot gain in halftone screens on laser printers. Its 'color separation' capability is rudimentary/first draft though and is ridiculously close to inverse RGB rather than CMYK. For good color seps we use Photoshop so I can control undercolor removal.
In the couple of prompts I gave it, it's better than the last version but I feel that Google is sacrificing quality for the sake of speed. While it's a lot faster, the output is not as good as OpenAI.
Meanwhile Veo3 is far better than the OpenAI's equivalent. I assume speed is not a priority there; both take their time.
I tried the following prompt and other than producing a four panel comic that was black and white it completely ignored every other instruction. This was with 4 ultra. Maybe someone else will have better luck but the failure seemed stable.
'''
A four panel comic strip. Simple black on white. Stick figures for characters. In the first panel there is a stick figure man and a stick figure bird eating bird seed at his feet. He is slightly hunched over to show he is looking at the bird. In the second panel. He is more hunched over looking more closely at the bird. In the third panel he is even more hunched over practically with his head to the bird, he is crouched down, knees bent, hands on thighs. In the upper left of the third panel the tip of an enormous beak can be seen, but it's only a few lines so could be anything. In the final panel the beak has gobbled up the man and his arms and legs are flailing outside of the beak while the small bird continues to eat birdseed on the ground.
'''
I've updated my GenAI Comparison site to include Imagen4 Ultra, so now we have four Google related generative models (Gemini Flash, Imagen3, Imagen4, and Imagen4 Ultra).
Despite claims that Ultra supports improved strict prompt adherence, we saw no evidence that it scored any better than Imagen 4 and in some cases seemed to ignore the prompt altogether (see the "Not the Bees" comic). In many cases, it also seemed much less steerable than Imagen3 requiring many of the prompts to be rewritten.
23 comments
[ 2.5 ms ] story [ 56.0 ms ] threadAlso, the prompt specifically ask "Panel 4 should show the cat and dog high-fiving" but the cat is high-fiving ... the cat. Personally I find this hallucinated plot twist good, it makes the ending a bit better. Although technically this is demonstrating a failure of the tool to follow the instructions from the prompt. Interesting choice of example for an official announcement.
It's and its are backwards. The latter breaks the possessive s rule.
Speaking of, the possessive s should _always_ be added, no reason to sometimes omit it if the name ends in an s.
Ass backwards, all of it.
For those commenting in the latter category, it might be worthwhile to read a bit about the underlying technology and share your insights on why it does not deliver.
Does the world need yet another AI slop generator?
https://i.imgur.com/kSuqCYg.jpeg
>The model may output text only. Try asking for image outputs explicitly (e.g. "generate an image", "provide images as you go along", "update the image").
>The model may stop generating partway through. Try again or try a different prompt.
Seriously?
One of the biggest corporations in the world and they can't re-read before posting a typo in the title.
Heads be shakin
Meanwhile Veo3 is far better than the OpenAI's equivalent. I assume speed is not a priority there; both take their time.
''' A four panel comic strip. Simple black on white. Stick figures for characters. In the first panel there is a stick figure man and a stick figure bird eating bird seed at his feet. He is slightly hunched over to show he is looking at the bird. In the second panel. He is more hunched over looking more closely at the bird. In the third panel he is even more hunched over practically with his head to the bird, he is crouched down, knees bent, hands on thighs. In the upper left of the third panel the tip of an enormous beak can be seen, but it's only a few lines so could be anything. In the final panel the beak has gobbled up the man and his arms and legs are flailing outside of the beak while the small bird continues to eat birdseed on the ground. '''
Despite claims that Ultra supports improved strict prompt adherence, we saw no evidence that it scored any better than Imagen 4 and in some cases seemed to ignore the prompt altogether (see the "Not the Bees" comic). In many cases, it also seemed much less steerable than Imagen3 requiring many of the prompts to be rewritten.
https://genai-showdown.specr.net?models=IMAGEN_3,IMAGEN_4,IM...
Result: https://imgur.com/a/Ri0yb31
This is supposed to be SOTA?