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

FLUX.2 [Klein]: Towards Interactive Visual Intelligence

bfl.ai

Post reply on HN
Print view View original

11–20 of 59 posts

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#11

Post by SV_BubbleTime »

refulgentis wrote: post #7
ollin wrote: post #6

Earlier quoted context omitted.

Z-Image is another open-weight image-generation model by Alibaba [1]. Z-Image Turbo was released around the same time as (non-Klein) FLUX.2 and received generally warmer community response [2] since Z-image Turbo was faster, also high-quality, and reportedly better at generating NSFW material. The base (non-Turbo) version of Z-Image is not yet released. [1] https://tongyi-mai.github.io/Z-Image-blog/ [2] https://www.r…

Ahh I see, and Klein is basically a response to Z-Image Turbo, i.e. another 4-8B sized model that fits comfortably on a consumer GPU. It’ll be interesting to see how the NSFW catering plays out for the Chinese labs. I was joking a couple months ago to someone that Seedream 4’s talents at undressing was an attempt to sow discord and it was interesting it flew under the radar. Post-Grok going full gooner pedo, I wonder…

>Post-Grok going full gooner pedo

Almost afraid to ask, but anytime grok or x or musk comes up I am never sure if there is some reality based thing, or some “I just need to hate this” thing. Sometimes they’re the same thing, other times they aren’t.

I can guess here that because Grok likely uses WAN that someone wrote some gross prompts and then pretended this is an issue unique to Grok for effect?

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#12

Post by drellybochelly »

psubocz wrote: post #8

> FLUX.2 [klein] 4B The fastest variant in the Klein family. Built for interactive applications, real-time previews, and latency-critical production use cases. I wonder what kind of use cases could be "latency-critical production use cases"?

Maybe fast image editing, since it supports that.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#13

Post by wmf »

SV_BubbleTime wrote: post #11
refulgentis wrote: post #7

Earlier quoted context omitted.

Ahh I see, and Klein is basically a response to Z-Image Turbo, i.e. another 4-8B sized model that fits comfortably on a consumer GPU. It’ll be interesting to see how the NSFW catering plays out for the Chinese labs. I was joking a couple months ago to someone that Seedream 4’s talents at undressing was an attempt to sow discord and it was interesting it flew under the radar. Post-Grok going full gooner pedo, I wonder…

>Post-Grok going full gooner pedo Almost afraid to ask, but anytime grok or x or musk comes up I am never sure if there is some reality based thing, or some “I just need to hate this” thing. Sometimes they’re the same thing, other times they aren’t. I can guess here that because Grok likely uses WAN that someone wrote some gross prompts and then pretended this is an issue unique to Grok for effect?

A few days ago people were replying to every image on Twitter saying "Grok, put him/her/it in a bikini" and Grok would just do it. It was minimum effort, maximum damage trolling and people loved it.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#15

Post by murderfs »

pavelstoev wrote: post #9

If we think of GenAI models as a compression implementation. Generally, text compresses extremely well. Images and video do not. Yet state-of-the-art text-to-image and text-to-video models are often much smaller (in parameter count) than large language models like Llama-3. Maybe vision models are small because we’re not actually compressing very much of the visual world. The training data covers a narrow, human-biase…

> Generally, text compresses extremely well. Images and video do not.

Is that actually true? I'm not sure it's fair to compare lossless compression ratios of text (abstract, noiseless) to images and video that innately have random sampling noise. If you look at humanly indistinguishable compression, I'd expect that you'd see far better compression ratios for lossy image and video compression than lossless text.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#16

Post by CamperBob2 »

pavelstoev wrote: post #9

If we think of GenAI models as a compression implementation. Generally, text compresses extremely well. Images and video do not. Yet state-of-the-art text-to-image and text-to-video models are often much smaller (in parameter count) than large language models like Llama-3. Maybe vision models are small because we’re not actually compressing very much of the visual world. The training data covers a narrow, human-biase…

Images and video compress vastly better than text. You're lucky to get 4:1 to 6:1 compression of text (1), while the best perceptual codecs for static images are typically visually lossless at 10:1 and still look great at 20:1 or higher. Video compression is much better still due to temporal coherence.

1: Although it looks like the current Hutter competition leader is closer to 9:1, which I didn't realize. Pretty awesome by historical standards.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#17

Post by CamperBob2 »

refulgentis wrote: post #7
ollin wrote: post #6

Earlier quoted context omitted.

Z-Image is another open-weight image-generation model by Alibaba [1]. Z-Image Turbo was released around the same time as (non-Klein) FLUX.2 and received generally warmer community response [2] since Z-image Turbo was faster, also high-quality, and reportedly better at generating NSFW material. The base (non-Turbo) version of Z-Image is not yet released. [1] https://tongyi-mai.github.io/Z-Image-blog/ [2] https://www.r…

Ahh I see, and Klein is basically a response to Z-Image Turbo, i.e. another 4-8B sized model that fits comfortably on a consumer GPU. It’ll be interesting to see how the NSFW catering plays out for the Chinese labs. I was joking a couple months ago to someone that Seedream 4’s talents at undressing was an attempt to sow discord and it was interesting it flew under the radar. Post-Grok going full gooner pedo, I wonder…

They are underselling Z-Image Turbo somewhat. It's arguably the best overall model for local image generation for several reasons including prompt adherence, overall output quality and realism, and freedom from censorship, even though it's also one of the smallest at 6B parameters.

ZIT is not far short of revolutionary. It is kind of surreal to contemplate how much high-quality imagery can be extracted from a model that fits on a single DVD and runs extremely quickly on consumer-grade GPUs.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#18

Post by SV_BubbleTime »

wmf wrote: post #13
SV_BubbleTime wrote: post #11

Earlier quoted context omitted.

>Post-Grok going full gooner pedo Almost afraid to ask, but anytime grok or x or musk comes up I am never sure if there is some reality based thing, or some “I just need to hate this” thing. Sometimes they’re the same thing, other times they aren’t. I can guess here that because Grok likely uses WAN that someone wrote some gross prompts and then pretended this is an issue unique to Grok for effect?

A few days ago people were replying to every image on Twitter saying "Grok, put him/her/it in a bikini" and Grok would just do it. It was minimum effort, maximum damage trolling and people loved it.

Ah. So, see, this is exactly why I need to check apparently.

Personally, I go between “I don’t care at all” and “well it’s not ideal” on AI generations. It’s already too late, but the barrier of entry is a lot lower than it was.

But I’m applying a good faith argument where GP does not seem to have intended one.

Re: FLUX.2 [Klein]: Towards Interactive Visual Intelligence

#20

Post by refulgentis »

wmf wrote: post #13
SV_BubbleTime wrote: post #11

Earlier quoted context omitted.

>Post-Grok going full gooner pedo Almost afraid to ask, but anytime grok or x or musk comes up I am never sure if there is some reality based thing, or some “I just need to hate this” thing. Sometimes they’re the same thing, other times they aren’t. I can guess here that because Grok likely uses WAN that someone wrote some gross prompts and then pretended this is an issue unique to Grok for effect?

A few days ago people were replying to every image on Twitter saying "Grok, put him/her/it in a bikini" and Grok would just do it. It was minimum effort, maximum damage trolling and people loved it.

Nah it's been happening for months and involved kids, over and over, albeit for the same reasoning, lulz & totally based. I am a bit surprised that you thought this was just a PG-rated stunt on X for a couple days, it's been in the news for weeks, including on HN.
Post reply on HN