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

Flux: Open-source text-to-image model with 12B parameters

blog.fal.ai

Post reply on HN
Print view View original

141–150 of 239 posts

Re: Flux: Open-source text-to-image model with 12B parameters

#141

Post by Morphiak »

Hizonner wrote: post #104
burkaygur wrote: post #32

hi friends! burkay from fal.ai here. would like to clarify that the model is NOT built by fal. all credit should go to Black Forest Labs ( https://blackforestlabs.ai/ ) which is a new co by the OG stable diffusion team. what we did at fal is take the model and run it on our inference engine optimized to run these kinds of models really really fast. feel free to give it a shot on the playgrounds. https://fal.ai/models…

You also might want to "clarify" that it is not open source (and neither are any of the other "open source" models). If you want to call it something, try "open weights", although the usage restrictions make even that a HUGE FUCKING STRETCH. Also, everybody should remember that these models are not copyrightable and you should never agree to any license for them...

A personal bugbear is the AI fascination with calling themselves open source, virtue signalling I guess. Open weights is exactly right. Source code and arguably more important datasets are both required to replicate the work, which is more in the spirit of open source (and science). I think Meta is especially egregious here, given their history.

Never underestimate the value of getting hordes of unpaid workers to refine your product. (See also React, others)

Re: Flux: Open-source text-to-image model with 12B parameters

#142

Post by simonw »

astromaniak wrote: post #116
Hizonner wrote: post #104

Earlier quoted context omitted.

You also might want to "clarify" that it is not open source (and neither are any of the other "open source" models). If you want to call it something, try "open weights", although the usage restrictions make even that a HUGE FUCKING STRETCH. Also, everybody should remember that these models are not copyrightable and you should never agree to any license for them...

> it is not open source It would be nice here if you give some examples of what you call open source model. Please ;) Because the impression is that these things do not exist, it's just a dream which does not deserve such a nice term..

I'm personally comfortable calling a model "open source" if the license is compatible with the https://opensource.org/ definition.

The Llama models aren't. Some of the Mistral models are (the Apache 2 ones). Microsoft Phi-3 is - it's MIT.

Re: Flux: Open-source text-to-image model with 12B parameters

#143

Post by Morphiak »

dheera wrote: post #47
minimaxir wrote: post #17

Earlier quoted context omitted.

Note that actually running the model without a A100 GPU or better will be tricker than usual given its size (12B parameters, 24GB on disk). There is a PR to that repo for a diffusers implementation, which may run on a cheap L4 GPU w/ enable_model_cpu_offload(): https://huggingface.co/black-forest-labs/FLUX.1-schnell/comm...

You don't need an A100, you can get a used 32GB V100 for $2K-$3K. It's probably the absolute best bang-for-buck inference GPU at the moment. Not for speed but just the fact that there are models you can actually fit on it that you can't fit on a gaming card, and as long as you can fit the model, it is still lightyears better than CPU inference.

Why this versus the 2 3090s (with nvlink for marginal gains) and 48GB for 2$K ?

Re: Flux: Open-source text-to-image model with 12B parameters

#144

Post by lukan »

TheAceOfHearts wrote: post #138
CGamesPlay wrote: post #134

Earlier quoted context omitted.

I mean, you can use a fork to make whipped cream, but it won't be easy and it's not the right tool for the job. Does that mean that the fork is useless?

I never said it was useless, just that it fails at this specific problem. One of my complaints with many of these image generation tools is that there's not much communication as to what should be expected from them, nor do they explain the areas where they're expected to succeed or fail. Recently Claude began to allow generation of SVG drawings, and asking it to draw a unicorn and later add extra tails or horns work…

"Recently Claude began to allow generation of SVG drawings, and asking it to draw a unicorn and later add extra tails or horns worked correctly."

That sounds interesting! Were the results somewhat clean and clear SVG or rather a mess that just looked decent?

Re: Flux: Open-source text-to-image model with 12B parameters

#145

Post by roenxi »

seveibar wrote: post #57

whenever I see a new model I always see if it can do engineering diagrams (e.g. "two square boxes at a distance of 3.5mm"), still no dice on this one. https://x.com/seveibar/status/1819081632575611279 Would love to see an AI company attack engineering diagrams head on, my current hunch is that they just aren't in the training dataset (I'm very tempted to make a synthetic dataset/benchmark)

It'll probably come suddenly. It has been fascinating to me watching the journey from Stable Diffusion 1 to 3. SD1 was a very crude model, where putting a word in the prompt might or might not add representations of the word to the image. Eg, using the word "hat" somewhere in the prompt might do literally nothing or suddenly there were hats everywhere. The context of the word didn't mean much to SD1.

SD2 was more consistent about the word appearing in the image. "hat" would add hats more reliably. Context started to matter a little bit.

SD3 seems to be getting a lot better at the idea of scene composition, so now specific entities can be prompted to wear hats. Not perfect, but noticeably improved from SD2.

Extrapolating from that, we're still a few generations from being able to describe things with the precision of an engineering diagram - but we're heading in the right direction at a rapid clip. I doubt there needs to be any specialist work yet, just time and the improvement of general purpose models.

Re: Flux: Open-source text-to-image model with 12B parameters

#146

Post by wmf »

mlboss wrote: post #113

These venture funded startups keep releasing models for free without a business model in sight. I am all for open source but worry it is not sustainable long term.

The free models are for practice and advertising. Once they get good they start charging. We've already seen this with Mistral and Stability.

Re: Flux: Open-source text-to-image model with 12B parameters

#147

Post by shiroiushi »

thequadehunter wrote: post #140
teamspirit wrote: post #95

Earlier quoted context omitted.

You weren’t kidding. Tried three times and all three were variations of the same[0]. [0] https://fal.media/files/elephant/gu3ZQ46_53BUV6lptexEh.png

The interesting part is that it does a good Joe Biden, but Trump always looks weird and alien. https://imgur.com/a/fgf6Jt3

[flagged]

Re: Flux: Open-source text-to-image model with 12B parameters

#148

Post by TheAceOfHearts »

lukan wrote: post #144
TheAceOfHearts wrote: post #138

Earlier quoted context omitted.

I never said it was useless, just that it fails at this specific problem. One of my complaints with many of these image generation tools is that there's not much communication as to what should be expected from them, nor do they explain the areas where they're expected to succeed or fail. Recently Claude began to allow generation of SVG drawings, and asking it to draw a unicorn and later add extra tails or horns work…

"Recently Claude began to allow generation of SVG drawings, and asking it to draw a unicorn and later add extra tails or horns worked correctly." That sounds interesting! Were the results somewhat clean and clear SVG or rather a mess that just looked decent?

Here's the screenshot [0] that was shared with me. It's obviously pretty basic, but Claude understood the correct location for where the horns and tails should be located. This looks like a clear iterative improvement over older models.

[0] https://imgur.com/Cc5uJNg

Re: Flux: Open-source text-to-image model with 12B parameters

#149

Post by jillesvangurp »

Hizonner wrote: post #117
astromaniak wrote: post #116

Earlier quoted context omitted.

> it is not open source It would be nice here if you give some examples of what you call open source model. Please ;) Because the impression is that these things do not exist, it's just a dream which does not deserve such a nice term..

As far as I know, none have been released. And it doesn't even really make sense, because, as I said, the models aren't copyrightable to begin with and therefore aren't licensable either. However, plenty of open source software exists. The fact that open source models don't exist doesn't excuse attempts to falsely claim the prestige of the phrase "open source".

> models aren't copyrightable to begin with

You are wrong about that. It's a file with numbers. Which makes it a database or dataset and very much protected by copyright. That's why licenses are needed. For the phone book, things like open street maps, and indeed AI models.

> The fact that open source models don't exist

The fact that many people (myself included) routinely download and use models distributed under OSI approved licenses (Apache V2, MIT, etc.) makes that statement verifiably wrong. And yes, I do check the license of stuff that I use as I work with companies that care about such matters.

> As far as I know ...

Now you know better.

Re: Flux: Open-source text-to-image model with 12B parameters

#150

Post by minitoar »

Carrok wrote: post #79
minimaxir wrote: post #60

Earlier quoted context omitted.

The logo has the same exact copyrighted typography as the real Vanity Fair logo. I've also reproduced the same-copyrighted-typography with other brands with identical composition as copyrighted images. Just asking it "Vanity Fair cover story about Shrek" at a 3:2 ratio gives it a composition identical to a Vanity Fair cover very consistently (subject is in front of logo typography partially obscuring it) The image li…

On my list of AI concerns, whether or not Vanity Fair has it’s copyright infringed does not appear.

First they came for fashion magazines, and I said nothing.
Post reply on HN