FAQ FAQ  Forum Search   Events   Register Register  Login Login

Using FLUX 1

Author
Almazar80 View Drop Down
Senior Member
Senior Member

Joined: 16 May 2008
Country: United States
Location: United States
Status: Offline
Posts: 3318
Post Options Post Options   Quote Almazar80 Quote  Post ReplyReply Direct Link To This Post Topic: Using FLUX 1
    Posted: 09 August 2024 at 03:26
Trying out the new FLUX model (FLUX 1 dev).

1. Generated using a prompt found on the net



2. A young woman praying (I created the prompt for this)




I used SwarmUI (ConfyUI in the backend) with the FLUX 1 dev model. Something different, but related to what I studied a long time ago (AI and Computer Science). I have been playing with stable diffusion to generate images, but like many people, the latest SD3 models leave something to be desired. In the last week or so, the original developers of stable diffusion released the FLUX 1 set of models. It was time to give it a try, and these images are the results of trying the FLUX 1 dev out for a few hours. The technology is very interesting. The only question is what images and other data do people use to create these models. No one really knows.

I have also been playing with the llama 3.1 70B model released by Meta. This is quite interesting. I am hoping to try to figure out how well this model works with extracting entities and other information from text, but for now, I am happily testing out it's chat GPT like capabilities using openllama.

I think there is a long way yet before these models will actually understand text in a contextual manner in a broad domain. Still, a lot has happened in the last few years and it's great that Meta released llama 3.1 for people to use. I just hope these technologies are put to good use. We shall see.

In the meantime, it's really interesting to see how several lines of text can be used to generate interesting images. With FLEX, the images at least deviate from the ones that SDXL and models based on it are able to generate (the people generation tend to result in similar looking people).   

Thanks for looking. And for putting up with the computer stuff.

Edited by Almazar80 - 09 August 2024 at 04:29
 



Back to Top
addy landzaat View Drop Down
Senior Member
Senior Member

Joined: 22 April 2006
Country: Netherlands
Location: Netherlands
Status: Offline
Posts: 15628
Post Options Post Options   Quote addy landzaat Quote  Post ReplyReply Direct Link To This Post Posted: 09 August 2024 at 08:06
What is FLUX?

Sounds like AI, but googling flux gives: f.lux, Wikipedia, Flux CD, E-flux by road, Flux taxatie software, Flux immersive audio software, Flux cloud computing and Flux landscape architecture.

Flux is such a non-descriptive name...
Why not follow me on Instagram? @Addy_101
Back to Top
AudioDoc View Drop Down
Senior Member
Senior Member

Joined: 26 January 2006
Country: United States
Location: SLC Utah
Status: Offline
Posts: 3516
Post Options Post Options   Quote AudioDoc Quote  Post ReplyReply Direct Link To This Post Posted: 09 August 2024 at 13:41
Flux is used when soldering! Sorry, couldn't resist!
Back to Top
Almazar80 View Drop Down
Senior Member
Senior Member

Joined: 16 May 2008
Country: United States
Location: United States
Status: Offline
Posts: 3318
Post Options Post Options   Quote Almazar80 Quote  Post ReplyReply Direct Link To This Post Posted: 09 August 2024 at 13:41
It is an AI model developed by the original researchers at Stabillity AI.

More info on FLUX

Not perfect, and you need a rather beefy video card (at least 12gb VRAM using the schnell model, 16gb to use the dev model). It does render hands much better than many previous models.
Back to Top
AudioDoc View Drop Down
Senior Member
Senior Member

Joined: 26 January 2006
Country: United States
Location: SLC Utah
Status: Offline
Posts: 3516
Post Options Post Options   Quote AudioDoc Quote  Post ReplyReply Direct Link To This Post Posted: 09 August 2024 at 13:44
Ah, ha, thank you Winston! And your photos are very nice! Beautiful portrait "A young woman praying"! TFS!

Kelly

The built in video in my Mac Mini M1 might not qualify for Flux!
Back to Top
addy landzaat View Drop Down
Senior Member
Senior Member

Joined: 22 April 2006
Country: Netherlands
Location: Netherlands
Status: Offline
Posts: 15628
Post Options Post Options   Quote addy landzaat Quote  Post ReplyReply Direct Link To This Post Posted: 09 August 2024 at 15:43
Ah, thank you for the link! They exist since 1 august. I will not comment on the use of German by this very American company

Interesting results. It is impressive, knowing it is AI I see some artifacts, but I wouldn't notice if I didn't know.
Why not follow me on Instagram? @Addy_101
 



Back to Top
pegelli View Drop Down
Admin Group
Admin Group
Dyxum Administrator

Joined: 02 June 2007
Country: Belgium
Location: Schilde
Status: Offline
Posts: 38252
Post Options Post Options   Quote pegelli Quote  Post ReplyReply Direct Link To This Post Posted: 14 August 2024 at 19:44
While these pictures are not really bad they are still easily recognised as AI generated.
My two biggest problems with AI generated images are:

First, they seem way overprocessed and too clean to be real photos.

Secondly there's no guarantee that all owners of the "real" photos to train the AI model and the people pictured in those photos have given their permission to use these photos for that purpose.
You can see the April Foolishness 2023 exhibition here Another great show of the talent we have on Dyxum
Back to Top
Almazar80 View Drop Down
Senior Member
Senior Member

Joined: 16 May 2008
Country: United States
Location: United States
Status: Offline
Posts: 3318
Post Options Post Options   Quote Almazar80 Quote  Post ReplyReply Direct Link To This Post Posted: 14 August 2024 at 19:47
You hit it on the head, but this model is a lot better than models that came out just a few months ago. The rate of improvement is staggering. Still, there probably was a lot of images used for training that were not properly licensed, but hopefully, that changes as well. In two years, this stuff will look like crude drawings.
Back to Top
LAbernethy View Drop Down
Senior Member
Senior Member

Joined: 25 November 2015
Country: Canada
Location: Ontario
Status: Offline
Posts: 3508
Post Options Post Options   Quote LAbernethy Quote  Post ReplyReply Direct Link To This Post Posted: 16 August 2024 at 02:03
I use to think Aldous Huxley had a more persuasive presentation of the future than George Orwell but the last 20 years have convinced me that Orwell had it right all along. AI imaging programs like this are a Ministry of Truth wet dream and a boon for child pornographers everywhere.
Back to Top
Almazar80 View Drop Down
Senior Member
Senior Member

Joined: 16 May 2008
Country: United States
Location: United States
Status: Offline
Posts: 3318
Post Options Post Options   Quote Almazar80 Quote  Post ReplyReply Direct Link To This Post Posted: 16 August 2024 at 03:48
AI imaging is an inevitability. It can be used for good or bad, as with everything else. To someone like me who went through classes in math that I have since forgotten (FFTs for edge detection, for example), it's fascinating. I am much more interested in using LLMs for entity extraction (from stories, newspaper articles, etc.).
Back to Top
Dyxum main page >  Forum Home > Dyxum Community > Open Talk

Forum Jump Forum Permissions View Drop Down



This page was generated in 0.078 seconds.

Monitor calibration strip

Dyxum.com - Home of the alpha system photographer

In memory of Cameron Hill - brettania

Feel free to contact us if needed.