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

81–90 of 239 posts

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

#81

Post by warkdarrior »

vessenes wrote: post #77
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…

Congrats Burkay - the model is very impressive. One area I’d like to see improved in a flux v2 is knowledge of artist styles. Flux cannot respond to requests asking for paintings in the style of David Hockney, Norman Rockwell, Edgar Degas, — it seems to have no fine art training at all. I’d bet that fine art training would further improve the compositional skills of the model, plus it would open up a range of uses th…

Have those artists given permission for their styles to be slurped up into a model?

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

#82

Post by CuriouslyC »

phkahler wrote: post #78
CuriouslyC wrote: post #18

Earlier quoted context omitted.

3090 TIs should be able to handle it without much in the way of tricks for a "reasonable" (for the HN crowd) price.

Why not on a CPU with 32 or 64 GB of RAM?

Performance, mostly. It'll work but image generation is shitty to do slowly compared to text inference.

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

#83

Post by treesciencebot »

Aardwolf wrote: post #76
treesciencebot wrote: post #28

You can try the models here: (available without sign-in) FLUX.1 [schnell] (Apache 2.0, open weights, step distilled): https://fal.ai/models/fal-ai/flux/schnell (requires sign-in) FLUX.1 [dev] (non-commercial, open weights, guidance distilled): https://fal.ai/models/fal-ai/flux/dev FLUX.1 [pro] (closed source [only available thru APIs], SOTA, raw): https://fal.ai/models/fal-ai/flux-pro

What's the difference between pro and dev? Is the pro one also 12B parameters? Are the example images on the site (the patagonia guy, lego and the beach potato) generated with dev or pro?

I think they are mainly -dev and -schnell. Both models are 12B. -pro is the most powerful and raw, -dev is guidance distilled version of it and -schnell is step distilled version (where you can get pretty good results with 2-8 steps).

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

#85

Post by GaggiX »

warkdarrior wrote: post #81
vessenes wrote: post #77

Earlier quoted context omitted.

Congrats Burkay - the model is very impressive. One area I’d like to see improved in a flux v2 is knowledge of artist styles. Flux cannot respond to requests asking for paintings in the style of David Hockney, Norman Rockwell, Edgar Degas, — it seems to have no fine art training at all. I’d bet that fine art training would further improve the compositional skills of the model, plus it would open up a range of uses th…

Have those artists given permission for their styles to be slurped up into a model?

Give me a sec, I will contact Edgar Degas with my telegraph.

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

#86

Post by frognumber »

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…

It would be nice to understand limits of the free tier. I couldn't find that anywhere. I see pricing, but I'm generating images without swiping my credit card.

If it's unlimited or "throttled for abuse," say that. Right now, I don't know if I can try it six times or experiment to my heart's desire.

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

#87

Post by zellyn »

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)

I have likewise been utterly unable to get it to generate images that look like preliminary rapid pencil sketches. Suggestions by experienced prompters welcome!

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

#88

Post by jncfhnb »

lovethevoid wrote: post #63
jncfhnb wrote: post #48

Earlier quoted context omitted.

It’ll need time for the goodies beyond the base model though I would guess

Works great as is right now, I can see some workflows being affected or having to wait for an update, but even those can do with some temporary workarounds (like having to load another model for later inpainting steps). So if you're wanting to experiment and have a 24GB card, have at it!

Yeah I mean like controlnet / ipadapter / animateddiff / in painting stuff

I don’t feel like base models are super useful. Most real use cases depend on being able to iterate on consistent outputs imo.

I have had a very bad experience trying to use other models to modify images but I mostly do anime shit and maybe styles are less consistently embedded into language for those models

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

#89

Post by Vinnl »

treesciencebot wrote: post #28

You can try the models here: (available without sign-in) FLUX.1 [schnell] (Apache 2.0, open weights, step distilled): https://fal.ai/models/fal-ai/flux/schnell (requires sign-in) FLUX.1 [dev] (non-commercial, open weights, guidance distilled): https://fal.ai/models/fal-ai/flux/dev FLUX.1 [pro] (closed source [only available thru APIs], SOTA, raw): https://fal.ai/models/fal-ai/flux-pro

> (available without sign-in) FLUX.1 [schnell] (Apache 2.0, open weights, step distilled): https://fal.ai/models/fal-ai/flux/schnell

Well, I was wondering about bias in the model, so I entered "a president" as the prompt. Looks like it has a bias alright, but it's even more specific than I expected...

Post reply on HN