Live data from Hacker News

FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

replicate.com

11–20 of 159 posts

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#11

"state of the art" has become such tired marketing jargon. "our most advanced and efficient model yet" "a significant step forward in our mission to empower creators" I get it, you can't sell things if you don't market them, and you can't make a living making things if you don't sell them, but it's exhausting.

The official blog post justifies the marketing copy a bit more with metrics.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#12

I'm worried about what happens when more people find out about Ideogram. There are a lot of things that don't appear in ELO scores. For one, they will not reflect that you cannot prompt women's faces in Flux. We can only speculate why.

What do you mean? FLUX.1 prompts women or women faces just fine? Do you mean the skin texture is unrealistic or some other artifacts?

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#13

"state of the art" has become such tired marketing jargon. "our most advanced and efficient model yet" "a significant step forward in our mission to empower creators" I get it, you can't sell things if you don't market them, and you can't make a living making things if you don't sell them, but it's exhausting.

Flux genuinely is the best model I’ve tried though. If there is a better one I’d love to know.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#14
post #8

Are there any projects that allow for easy setup and hosting Flux locally? Similar to SD projects like InvokeAI or a1111

Flux is more weird than old SD projects since Flux is extremely resource dependant and won't run on most hardware.

The GGUF quantisations do run on most recent hardware, albeit at increasingly concerning quality tradeoffs.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#15
post #7

The generated images look impressive of course but I can't help but be mildly amused by the fact that the prompt for the second example image insists strongly that the image should say 1.1: > ... photo with the text "FLUX 1.1 [Pro]", ..., must say "1.1", ... ...And of course, it does not.

[flagged]

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#16

I'm worried about what happens when more people find out about Ideogram. There are a lot of things that don't appear in ELO scores. For one, they will not reflect that you cannot prompt women's faces in Flux. We can only speculate why.

How locked down is it? My problem with a lot of these is I like to make really ridiculous meme type images, but I run into walls for dumb reasons. Like if I want to make something thats "copyrighted" like a mix of certain characters from one franchise or whatever, I cannot sometimes I get told that the model cannot generate copyrighted content, even though courts ruled that AI generated stuff cannot be copyrighted ei…

> How locked down is it? ... I get told that the model cannot generate copyrighted... AI should just be treated as fair use

Ideogram and Flux both have their own broad set of limitations that are non-technical and unpublished. IMO they are not really motivated by legal concerns, other than the lack of transparency itself.

So maybe the issue is that transparency, and that the hazy legal climate means no transparency. You can't go anywhere and see the detailed list of dataset collection and captioning opinions for proprietary models. Open Model Initiative, trying to make a model, did publish their opinions, and they're not getting sued anytime soon. However, their opinions are an endless source of conflict.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#19
post #12

I'm worried about what happens when more people find out about Ideogram. There are a lot of things that don't appear in ELO scores. For one, they will not reflect that you cannot prompt women's faces in Flux. We can only speculate why.

What do you mean? FLUX.1 prompts women or women faces just fine? Do you mean the skin texture is unrealistic or some other artifacts?

Flux will not adhere to your detailed description of a woman's face nearly as well as it does for a man, and it doesn't adhere to text descriptions of faces well in general. This is not a technical limitation, this was a choice in the captioning of the model's dataset and maybe other more sophisticated decisions like loss. It exhibits similar flaws with its representation of male versus female celebrities; it also exhibits this flaw when you use language that describes male celebrities versus female celebrities appearances.

Re: FLUX1.1 [pro] – New SotA text-to-image model from Black Forest Labs

#20
post #8

Are there any projects that allow for easy setup and hosting Flux locally? Similar to SD projects like InvokeAI or a1111

Flux is more weird than old SD projects since Flux is extremely resource dependant and won't run on most hardware.

People have Flux running on pretty much everything at this point, assuming you are comfortable waiting 3+ minutes for a 512x512 image.

I managed to get it running on an old computer with a 2060 Super, taking ~1.5 minutes per image gen. People are generating on a 1080.

Post reply on HN