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

Flux 3

bfl.ai

Post reply on HN
Print view View original

131–140 of 151 posts

Re: Flux 3

#131

Post by deadbabe »

roenxi wrote: post #48
ra wrote: post #22

Earlier quoted context omitted.

It would be interesting to see some time-series sentiment analysis of HN. Subjectively it feels like there's much negativity on HN these days, I hope I'm wrong.

Bunch of software engineers are worried about their future employment prospects.

IMO it’s best to just stop worrying and embrace it as the end of days for the field.

These are the last good ol’ days you will have before it’s all over. Worrying about it won’t change the future. Just try to focus on all the good AI does.

Re: Flux 3

#132

Post by deadbabe »

rclkrtrzckr wrote: post #80
roenxi wrote: post #48

Earlier quoted context omitted.

Bunch of software engineers are worried about their future employment prospects.

s/software engineers/filmmakers/

filmmakers have the most to gain here, now anyone with a good idea for a story can just prompt out their own full length movie or tv show.

Re: Flux 3

#133

Post by potsandpans »

3form wrote: post #28
user43928 wrote: post #10

I hope the open-weight versions will be SOTA. > Over the next few weeks and months, we will make the following capabilities available > Open-weight access to a multimodal backbone, for content creation (video, audio and image) and action prediction. (“FLUX 3 Dev”) > We will also release more technical details on the underlying approach.

Open-weight promise seems nice, but 1) I've seen people commenting that these hopes amounted to nothing for some previous releases (no idea which promises were made though); and 2) if the backbone is released as Dev, what will be missing? I can't easily tell from the post.

Flux2.dev and even klein 9b are extremely close to sota. People who are saying otherwise probably haven't used them very much.

Re: Flux 3

#134

Post by vunderba »

potsandpans wrote: post #133
3form wrote: post #28

Earlier quoted context omitted.

Open-weight promise seems nice, but 1) I've seen people commenting that these hopes amounted to nothing for some previous releases (no idea which promises were made though); and 2) if the backbone is released as Dev, what will be missing? I can't easily tell from the post.

Flux2.dev and even klein 9b are extremely close to sota. People who are saying otherwise probably haven't used them very much.

I run a fairly high-traffic site for generative image models focusing on complex prompt adherence. Flux.2 doesn’t score anywhere near SOTA proprietary models.

Klein 9b is decent for image-to-image, but when used for pure generative purposes brings back SDXL levels of body horror (have some Gattica pianists).

If you can get past the annoying JSON structuring, Ideogram 4 is probably the best option in the open‑weights world right now for text2image purposes, and even scored higher than the original Nano-Banana.

For ref: Flux.2 scored 5, Ideogram4 scored 8, and gpt-image-2 scored 12 out of 15.

Comparison of Flux.2 [dev], Ideogram4, NB Pro, and gpt-image-2.

https://genai-showdown.specr.net/?models=nbp,f2d,g2,id4

Re: Flux 3

#135

Post by vunderba »

3form wrote: post #28
user43928 wrote: post #10

I hope the open-weight versions will be SOTA. > Over the next few weeks and months, we will make the following capabilities available > Open-weight access to a multimodal backbone, for content creation (video, audio and image) and action prediction. (“FLUX 3 Dev”) > We will also release more technical details on the underlying approach.

Open-weight promise seems nice, but 1) I've seen people commenting that these hopes amounted to nothing for some previous releases (no idea which promises were made though); and 2) if the backbone is released as Dev, what will be missing? I can't easily tell from the post.

Most of the disappointment around the previous open‑weight BFL release (at least for Flux.2 [dev]) came down to two main issues:

• It initially required significantly more VRAM and was much slower than alternatives released around the same time (like Z‑Image Turbo).

• The license felt overly restrictive.

Re: Flux 3

#136

Post by inquirerGeneral »

walrus01 wrote: post #83
user43928 wrote: post #81

Earlier quoted context omitted.

My issue with comments around the impact of AI is that often they are just not interesting. What substance is there beyond "I don't like it, and I think it is a negative for society", typically delivered with what I perceive as a self-righteous attitude?

My criticism is specifically with the use of text-to-image and text-to-video generators that will create fully artificial video and image content. I've seen the uses that these tools are being put to in 2025/2026 for electoral manipulation, social issue manipulation and it leaves me with a very distasteful impression. You will not see me leaving comments such as this, for example, on the release of a "strong in codin…

[dead]

Re: Flux 3

#137

Post by downrightmike »

forgotusername6 wrote: post #110

Is anyone feeding models touch data? It seems the main thing we want the robots to do is touch things, but we are just feeding them audio/video/images. The model has to learn how to touch things despite never having touched anything before. Perhaps that's why they all look so hesitant when they touch things?

Its faster to just have them simulate touching things, they figure it out way faster that way

Re: Flux 3

#138

Post by popalchemist »

user43928 wrote: post #53
vouaobrasil wrote: post #33

Earlier quoted context omitted.

It's possible it's because some people care about the consequences of what we're doing as a society beyond the mindless satiation of curiosity. Nothing wrong with curiosity in my books by the way, but I do think isolating it the way we've done in the technical fields is a dangerous and irresponsible attitude.

As I understand it HN is a community for hackers to discuss interesting and curious topics. Pessimistic opinions on the labor market, views about society and politics that border on the dystopian, as well as exaggerated concerns about datacenter environmental impacts, all seem like a poor fit for this website.

It is precisely those people who have abdicated such concerns who most need the discussion. You can not compartmentalize reality, even if you can compartmentalize your own mind. These discussions lead one closer to a relationship with reality as-it-is than as your mind would like it to be.

Re: Flux 3

#139

Post by CamperBob2 »

deadbabe wrote: post #132
rclkrtrzckr wrote: post #80

Earlier quoted context omitted.

s/software engineers/filmmakers/

filmmakers have the most to gain here, now anyone with a good idea for a story can just prompt out their own full length movie or tv show.

Before AI: 90% of everything was crap

After AI: 99% of everything is crap

... but there will be >10x more of it, so we'll ultimately end up with more good stuff.

Re: Flux 3

#140

Post by isoprophlex »

vrganj wrote: post #123
AmbroseBierce wrote: post #122

Amazing. This will be fundamental for the future for robots to distinguish the sound of the poors getting close to Besos/Musk's/Zuckerberg bunkers and quickly adapt to any new kind of attack by the masses, robots will quickly learn to adapt to the behavior of the attackers, quickly infer where they are grouped, their numbers and so for. Of course there will be feuds from robots of different family groups but they wil…

When they hide in their bunkers, who's to stop people from pouring concrete down the ventilation shafts?

Or aerosolized LSD...
Post reply on HN