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

101–110 of 239 posts

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

#101

Post by seveibar »

napoleongl wrote: post #69
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)

Can’t you get this done via an LLM and have it generate code for mermaid or D2 or something? I’ve been fiddling around with that a bit in order to create flowcharts and datamodels, and I’m pretty sure I’ve seen at least one of those languages handle absolute positioning of object.

it usually isn't accurate. LLMs generally have very little spatial awareness.

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

#102

Post by msikora »

nextos wrote: post #45
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…

The name is a bit unfortunate given that Julia's most popular ML library is called Flux. See: https://fluxml.ai . This library is quite well known, 3rd most starred project in Julia: https://juliapackages.com/packages?sort=stars . It has been around since, at least, 2016: https://github.com/FluxML/Flux.jl/graphs/code-frequency .

Also Flux is a now obsolete application architecture for ReactJS.

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

#103

Post by spywaregorilla »

CuriouslyC wrote: post #93
spywaregorilla wrote: post #92

Earlier quoted context omitted.

custom models perform vastly better at the tasks they are finetuned to do

That is technically true, but when the base model is wasting parameter information on poorly tagged, watermarked stock art and other garbage images, it's not really a meaningful distinction. Better data makes for better models, nobody cares about how well a model outputs trash.

Ok, but you're severely misrepresenting the importance of things. Base SDXL is a fine model. Base SDXL is going to be much better than a materially smaller model that you've retrained with "good data".

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

#104

Post by Hizonner »

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...

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

#105

Post by dheera »

nextos wrote: post #45
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…

The name is a bit unfortunate given that Julia's most popular ML library is called Flux. See: https://fluxml.ai . This library is quite well known, 3rd most starred project in Julia: https://juliapackages.com/packages?sort=stars . It has been around since, at least, 2016: https://github.com/FluxML/Flux.jl/graphs/code-frequency .

I think we've generally run out of names to give projects and need to start reusing names. Maybe use letters to disambiguate them.

Flux A is the ML library

Flux B is the T2I model

Flux C is the React library

Flux D is the physics concept of power per unit area

Flux E is the goo you put on solder

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

#107

Post by metadat »

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…

The playground is a drag. After accepting being forced to sign up, attach my GitHub, and hand over my email address, I entered the desired prompt and waited with anticipation.. Only to see a black screen and how much it's going to cost per megapixel.

Bummer. After seeing what was generated in the blog post I was excited to try it! Now feeling disappointed.

I was hoping it'd be more like https://play.go.dev.

Good luck.

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

#108

Post by viraptor »

zarmin wrote: post #29

WILD Photo of teen girl in a ski mask making an origami swan in a barn. There is caption on the bottom of the image: "EAT DRUGS" in yellow font. In the background there is a framed photo of obama https://i.imgur.com/RifcWZc.png Donald Trump on the cover of "Leopards Ate My Face" magazine https://i.imgur.com/6HdBJkr.png

It got confused with the mask and origami unfortunately.

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

#110

Post by mft_ »

metadat wrote: post #107
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…

The playground is a drag. After accepting being forced to sign up, attach my GitHub, and hand over my email address, I entered the desired prompt and waited with anticipation.. Only to see a black screen and how much it's going to cost per megapixel. Bummer. After seeing what was generated in the blog post I was excited to try it! Now feeling disappointed. I was hoping it'd be more like https://play.go.dev . Good luc…

https://replicate.com/black-forest-labs/flux-dev is working very nicely. No sign-up.
Post reply on HN