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

71–80 of 239 posts

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

#71

Post by RobotToaster »

minimaxir wrote: post #10

The [schnell] model variant is Apache-licensed and is open sourced on Hugging Face: https://huggingface.co/black-forest-labs/FLUX.1-schnell It is very fast and very good at rendering text, and appears to have a text encoder such that the model can handle both text and positioning much better: https://x.com/minimaxir/status/1819041076872908894 A fun consequence of better text rendering is that it means text watermarks…

How does the licence work when there's a bunch of restrictions at the bottom of that page that seem to contradict the licence?

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

#72

Post by minimaxir »

RobotToaster wrote: post #71
minimaxir wrote: post #10

The [schnell] model variant is Apache-licensed and is open sourced on Hugging Face: https://huggingface.co/black-forest-labs/FLUX.1-schnell It is very fast and very good at rendering text, and appears to have a text encoder such that the model can handle both text and positioning much better: https://x.com/minimaxir/status/1819041076872908894 A fun consequence of better text rendering is that it means text watermarks…

How does the licence work when there's a bunch of restrictions at the bottom of that page that seem to contradict the licence?

IANAL but I suspect that "Out-of-Scope Use" has no legal authority.

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

#73

Post by CuriouslyC »

dinobones wrote: post #20

I wonder if the key behind the quality of the MidJourney models, and this models, is less about size + architecture and more about the quality of images trained on. It looks like this is the case for LLMs, that the training quality of the data has a significant impact on the output quality of the model, which makes sense. So the real magic is in designing a system to curate that high quality data.

Midjourney unquestionably has heavy data set curation and uses RLHF from users.

You don't have to speculate on this as you can see that custom models for SDXL for instance perform vastly better than vanilla SDXL at the same number of parameters. It's all data set and tagging.

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

#74

Post by RobotToaster »

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 is the difference between schnell and dev? Just the kind of distillation?

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

#75

Post by dabeeeenster »

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 unsubscribe links in your emails don't work

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

#76

Post by Aardwolf »

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?

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

#77

Post by vessenes »

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 that are (to me at least) a bit more interesting than just illustrations.

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

#78

Post by phkahler »

CuriouslyC wrote: post #18
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...

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?

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

#79

Post by Carrok »

minimaxir wrote: post #60
nwoli wrote: post #59

Earlier quoted context omitted.

That’s not really fair to conclude that the training data contains vanity fair images since the prompt includes “by Vanity Fair”. I could write “with text that says Shutterstock” in the prompt but that doesn’t necessairly mean the dataset contains that

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.

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

#80

Post by phkahler »

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)

>> 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)

That seems like a good use for a speech driven assistant that know how to use PC desktop software. Just talk to a CAD program and say what you want. This seems like a long way off but could be very useful.

Post reply on HN