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

FLUX is fast and it's open source

replicate.com

Post reply on HN
Print view View original

11–20 of 127 posts

Re: FLUX is fast and it's open source

#11

Post by Vt71fcAqt7 »

lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

>Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting.

Re: FLUX is fast and it's open source

#12

Post by worstspotgain »

lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

https://podcasts.apple.com/us/podcast/what-the-flux/id149389...

Re: FLUX is fast and it's open source

#13

Post by swyx »

this comparison for the quantization effect is very nice https://flux-quality-comparison.vercel.app/

however i do have to ask.. ~2x faster for fp16->fp8 is expected right? its still not as good as the "realtime" or "lightning" options that basically have to be 5-10x faster. whats the ideal product usecase for just ~2x faster?

Re: FLUX is fast and it's open source

#14

Post by dang »

lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

"Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting."

https://news.ycombinator.com/newsguidelines.html

Re: FLUX is fast and it's open source

#15

Post by lolinder »

Vt71fcAqt7 wrote: post #11
lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

>Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting.

In general I think that's true and agree that minor name collision commentary is uninteresting, but in this case we're talking about 11 collisions (and counting) in tech alone, 3 of those in AI/ML and 1 of those specifically in image generation.

When it's that bad I think that the frequency of collisions for this name is an interesting topic in its own right.

Re: FLUX is fast and it's open source

#17

Post by bigiain »

Conscat wrote: post #5
lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

The first thing that comes to mind when I think "flux" is none of the above too . There's an extremely cool alternative iterator library for C++20 by Tristan Brindle named flux.

/me glances across my desk to see my soldering station...

Re: FLUX is fast and it's open source

#18

Post by lolinder »

dang wrote: post #14
lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

" Please don't complain about tangential annoyances—e.g. article or website formats, name collisions, or back-button breakage. They're too common to be interesting. " https://news.ycombinator.com/newsguidelines.html

I just posted a reply to another person quoting this guideline:

> In general I think that's true and agree that minor name collision commentary is uninteresting, but in this case we're talking about 11 collisions (and counting) in tech alone, 3 of those in AI/ML and 1 of those specifically in image generation.

> When it's that bad I think that the frequency of collisions for this name is an interesting topic in its own right.

I'll respect your judgement on this and not push it further, but this is my thought process here.

Re: FLUX is fast and it's open source

#19

Post by dig1 »

lolinder wrote: post #2

I know naming things is hard, but... https://justgetflux.com/ https://flux11pro.com/ (Maybe the same thing? Unclear.) https://github.com/flux-framework/flux-core https://github.com/facebookarchive/flux/tree/main (apparently archived now, but this was the first thing I thought of) https://www.flux.ai/ https://fluxcd.io/ https://runonflux.io/ https://fluxml.ai/

Also https://github.com/influxdata/flux - "a lightweight scripting language for querying databases and working with data"

Re: FLUX is fast and it's open source

#20

Post by weird-eye-issue »

swyx wrote: post #10

> We added a new synchronous HTTP API that makes all image models much faster on Replicate. ooh why is synchronous fast? i click thru to https://replicate.com/changelog/2024-10-09-synchronous-api > Our client libraries and API are now much faster at running models, particularly if a file is being returned. ... thanks? just sharing my frustration as a developer. try to explain things a little better if you'd like it t…

I mean it literally explains why in the second paragraph. It returns the actual file data in the response rather than a URL where you have to make a second request to get the file data
Post reply on HN