OpenAI’s DALL-E 3-Like AI For Free, Forever!

Flux is available here:

Try it:

Run it yourself at home:

Image credit:

📝 My paper on simulations that look almost like reality is available for free here:

Or this is the orig. Nature Physics link with clickable citations:

🙏 We would like to thank our generous Patreon supporters who make Two Minute Papers possible:
Alex Balfanz, Alex Haro, B Shang, Benji Rabhan, Gaston Ingaramo, Gordon Child, John Le, Kyle Davis, Loyal Alchemist, Lukas Biewald, Martin, Michael Albrecht, Michael Tedder, Owen Skarpness, Richard Sundvall, Taras Bobrovytsky, Ted Johnson, Thomas Krcmar, Tybie Fitzhugh, Ueli Gallizzi.

[ConnorisseurYT]

1 minute in and I already dropped my papers

[jonmichaelgalindo]

This is much better than DallE3 in my physics tests. It passed "Hand holding a pair of scissors casting a shadow on a wall" 😊🎉

[viddarkking]

A group of AI researchers leave Stability recruit a friend beat Stability at their own game.
Love to see it.

[Yenrabbit]

Exciting model! But I wish the title wasn't focused on Dalle 3?

[EVILBUNNY]

I love this, hopefully it makes Dale-3 and Midjourney creators rethink how much they charge for their own models.

[oguretsagressive]

3:06 "problem: you get an additional llama you can't get rid of" 🤣

[smorty]

Hey Károly! The title of your video made me think that Open AI actually released an open model for once... It may confuse other fellow scholars as well, so maybe consider changing it somewhat.
Also I would have liked it if you had mentioned that there are two variants of the model, but that's just my take.

[whatworld]

I ahve to admit, I was skeptical about flux, but I got it to run on my local machine. It maxes out my system but on first load it takes a bout 416 secs to render an image, but after that just 100 secs. Though I am using the slimed down model Schenlle but still great results! Better than what I got with SD

[cesarkopp]

I thought the web version was free too. Silly me....
"You have -1 credits remaining. Upgrade to get more credits. An average creation costs 1-5 credits."

[muhammadlufti]

Been using this model for 3 days and I can’t believe that Flux Schnell model is that fast and Flux Pro model’s result is on par with Midjourney’s and Stable Ultra model

[roguegryphonica]

Flux suffers from additional appendage, and mystery appendage syndrome. It also doesn't have a sense of direction. I generated a man flying a plane backwards. It also doesn't generate images well that aren't tropes. For example, it took me four or five tries to create a b horror masterpiece with the right zing. Text sometimes randomly appears in the image even if unprompted.

[CartoType]

This is incredible. I tried it a few minutes ago, and it's going to take me some time to recover from my amazement. I asked for a picture in the style of a Victorian painting with ancient Indo-European chieftains and a mass of their followers, and got an extremely good result.

[khalatelomara]

I tried it and it is impressive quite close to keep patterns and details for architecture

[Adreitz]

I'm running Flux dev on my own machine and its results are GREAT. Very coherent and aesthetic, and the amount of detail is outstanding -- the output is full of pixel-level features, so I wouldn't be surprised if it is using a 16-channel VAE like SD3. The drawbacks are 1. this model is HEAVY at 12B parameters plus T5 (you'll probably need at least 12GB VRAM to run it, and quantized at that); 2. if you thought SDXL was slow, this is about 4x slower step-for-step; 3. it currently doesn't support negative prompts as far as I know, so that may cause problems if your desired prompt causes the model to add undesired features to the image (e.g. "make me a photo of fried rice without peas"). Hopefully, Black Forest will make this into a model family including lower-weight options and put out their paper soon so others can learn from their advances.

[Juan-qvnc]

1:01 Now we are talking. I knew it it was going to be only two papers down the line! What a time for scholars to hold two minute papers... alive! 🙂

[ilakya]

Still a little bit too large to chew at home. But I also remembered back then when 13b parameters LLM were impossible to run at home too.

[Onihikage]

Dr. Károly, I know it's not quite your usual thing, but I would be very interested to see a video summarizing the major public advancements that have been made in cloth simulations over the last five or ten years. What kind of performance gains have been realized by the kind of research you've covered? What sort of real-time cloth simulation, such as in video games, has gone from unthinkable to trivial? I'd love to know! Maybe it's more suitable for a TwentyMinutePapers kind of video, but I really want to see it!

[mirek]

Flux iis insane .. I run it locally with rtx 3090 and comfyui, image is ready after 20 seconds
Wtit Flux dev quality is better than MJ or Dalle-3

[Eagleizer]

Tried it. It is terrible. I tried to make an all black rally car without plates with a number on the door. I instructed it to use wide angle lens and take picture from a distance. I even asked for black paint where the plates would be. Also asked for picture to be taken from an elevated position with the sun coming from behind the camera. Every time, there would be plates, sometimes with numbers, number on the door would be wrong 90% of the time, all pictures would be taken from ground level, and from very close. Dust cloud would often be in front of the car, and I never got the sun from behind the camera as instructed. After 100 or so generations I gave up. Every time i specified some areas with problems it would mess up something else. It also seemed to get stuck in a certain look, just as we see in all the fake video thumbnails on YouTube, you learn to see what it's doing and recognize it. Maybe this is good for some type of design, but the results I got with this was no better, and in fact VERY similar to the thumb creator in udio.

[giusepperana]

The one their API runs apparently is called the "Pro" model and isn't available for download.