I'm really impressed at its ability to output pixel art sprites. Maybe the best general-purpose model I've seen capable of that. In many cases its better than purpose-built models.
Flux: Open-source text-to-image model with 12B parameters
41–50 of 239 posts
Re: Flux: Open-source text-to-image model with 12B parameters
#42Hey, great work over at fal.ai to run this on your infrastructure and for building in a free $2 in credits to try before buying. For those thinking of running this at home, I'll save you the trouble. Black Forest Flux did not run easily on my Apple Silicon MacBook at this time. (Please let me know if you have gotten this to run for you on similar hardware.) Specifically, it falls back to using CPU which is very slow. Changing device to 'mps' causes error "BFloat16 is not supported on MPS"
Re: Flux: Open-source text-to-image model with 12B parameters
#43hi 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…
> We are excited to introduce Flux I'd suggest re-wording the blog post intro, it reads as if it was created by Fal. Specific phrases to change: > Announcing Flux (from the title) > We are excited to introduce Flux > Flux comes in three powerful variations: This section also comes across as if you created it > We invite you to try Flux for yourself. Reads as if you're the creator
Thanks for the feedback! Made some updates.
Re: Flux: Open-source text-to-image model with 12B parameters
#44Seems to do pretty poorly with spatial relationships. "An upside down house" -> regular old house "A horse sitting on a dog" -> horse and dog next to eachother "An inverted Lockheed Martin F-22 Raptor" -> yikes https://fal.media/files/koala/zgPYG6SqhD4Y3y_E9MONu.png
It appears the model does have some "sanity" restrictions from whatever its training process is that limits some of the super weird outputs.
"A horse sitting on a dog" doesn't work but "A dog sitting on a horse" works perfectly.
Re: Flux: Open-source text-to-image model with 12B parameters
#45hi 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.
Re: Flux: Open-source text-to-image model with 12B parameters
#46This is amazing! I thought it would be a few more years before we would have a such high quality model we could run locally.
Re: Flux: Open-source text-to-image model with 12B parameters
#47Earlier quoted context omitted.
Thank you. Their website is super hard to navigate and I can't find a "DOWNLOAD" button.
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.
Re: Flux: Open-source text-to-image model with 12B parameters
#48Re: Flux: Open-source text-to-image model with 12B parameters
#49Earlier quoted context omitted.
> We are excited to introduce Flux I'd suggest re-wording the blog post intro, it reads as if it was created by Fal. Specific phrases to change: > Announcing Flux (from the title) > We are excited to introduce Flux > Flux comes in three powerful variations: This section also comes across as if you created it > We invite you to try Flux for yourself. Reads as if you're the creator
Thanks for the feedback! Made some updates.
Way better, nice
Re: Flux: Open-source text-to-image model with 12B parameters
#50Seems to do pretty poorly with spatial relationships. "An upside down house" -> regular old house "A horse sitting on a dog" -> horse and dog next to eachother "An inverted Lockheed Martin F-22 Raptor" -> yikes https://fal.media/files/koala/zgPYG6SqhD4Y3y_E9MONu.png