Local Flux.1 LoRA Training Using Ai-Toolkit

Flux.1 is great at generating images, but you may find some styles difficult to prompt for. LoRAs are a great way to more easily generate styles, objects or people using Flux, and now you can make them at home, on your own PC!

At the moment you'll need a hefty 24GB VRAM, but who knows how low this will go in the future?

Patreon post for this video including workflows & more!

Want to support the channel?

Links:

== Beginners Guides! ==

[deastman]

It’s exciting to see how Flux support is developing so rapidly! Between Lora training and ControlNet, we’re just about to the point where we can bid farewell to SD entirely.

[dog]

I dropped a like because I love you man. As for the content, I can barely work out a sky remote. My son literally showed me a button I can press on my Sky remote so I can ask for what I want to watch. I wish I kept up with tech as you have. I started out good because I was a proud owner of a ZX81 and a 16K ZX Spectrum. I bought a chip from Radio Shack to change it to a 128K Spectrum. It broke. Gave up after my Commodore 64.

[TransformXRED]

Most people don't know but the Florenc2 model is very versatile and can be used for OCR. And OCR of handwriting text too, which is pretty hard to do.

[ThoughtFission]

Nice! Just stepping into the Lora chasm and this will really help

[tekkdesign]

This is incredible! I've learned more in 15 minutes than I did in a month of watching YouTube videos.

[juanjesusligero]

Oh, Nerdy Rodent, 🐭💻
he really makes my day; 😊✨
showing us AI, 🤖📊
in a really British way. ☕🎩

[Vyviel]

Thanks for this always love your videos! Hardest part looks to be the dataset so really appreciate the auto tagging workflow part. Do you have any tips for datasets for subjects rather than styles? Should I mix close up face shots and full body shots? Have you tried any other training tools like kohya-ss?

[gilgamesh.....]

I had trouble with u-kiyoe art as well. Flux is great at specific things but I think a lot of loras are going to be needed with it.

[contrarian]

@Nerdy Rodent Maybe a stupid question: can Loras trained for SD1.5/XL be applied to Flux models?

[krnondemand]

Great stuff! Could you share workflow for Florenc2

[PimentelES]

Nerdy, would you say that Ai-Toolkit is better than simpletuner for flux lora training?

[JurassicJordan]

Pls when training on lower vram comes out, make a vid on that

[EvilNando]

hello, whenever I try to launch the AI script I get the following: ModuleNotFoundError: No module named 'dotenv'
any ideas? (have pyton and git already installed)

[neonlost]

awesome video is there a way to use multi GPUs though? i have 3 3090

[diego]

god damn i finally mastered khoya and now have to use another trainer
( that's the one thing so frustrating with ai with each update half of the shit breaks) hope it will come to khoya as well

[cleverestx]

Thanks for the video, but @5:16 it would be nice if you could expand on how to do this entire section with the "run it the first time" (run what?), and how to make that .ENV file (folder?), I'm using WSL Ubuntu in Windows 11 (installing Linux version)

Under accepting model license it says, "Make a file named .env in the root on this folder"

What root? On hugging face itself; is that "THIS FOLDER", or the ai-toolkit root folder we just made using the instructions above? The instructions on the Github for this part needs to be less vague, or am I just that thick?

[moezgholami]

Hi, Thanks for the video. Can you tell us how many images you used to train the style LoRA for Flux? And whether you used any augmentation?

[Enigmo]

is there a way to do this without all the huggingface connection. i already have the model downloaded to a separate location on my PC...don't wanna waste time downloading it again

[davidmartinrius]

Hi there! I was wondering if it's possible to train a single LORA model to recognize and generate multiple specific faces or bodies of specific persons. For example, could one LORA model be used to generate both my own face and the faces of others based on their names? How to manage this with the trigger words?
I have a single dataset with all people tagged by its name and a short caption in the .txt files

[GerardMenvussa]

24GB of VRAM lol
Might as well hire a freelance artist to draw things for you at that price :o)