Flux 1 Dev LoRA Training Locally Using AI-ToolKit - Tutorial Guide

Flux 1 Dev LoRA Training Locally Using AI-ToolKit - Tutorial Guide

In today's video, we dive into the fascinating world of Flux diffusion models and training LoRA models to create stunning images. Join me as we explore the AI Toolkit GitHub project and learn how to install and configure the necessary components for this cutting-edge technology. From setting up the environment to training the models, we cover it all in detail. Stay tuned for a deep dive into the world of AI video scenes and image generation with Flux!

Additionial Tutorial Related To Flux LoRA Training

Learn how to train LoRA models for Flux diffusion to create consistent image styles! This tutorial walks you through the entire process, from installation to testing.

We cover:
00:00 - About Flux Lora Training
00:36 - Installing AI Toolkit on Windows
03:06 - Preparing datasets with image captioning
05:20 - Configuring LoRA training settings
07:06 - Using Hugging Face tokens for model access
07:35 - Running the training process
10:02 - Testing LoRA models in ComfyUI

Perfect for AI artists and video creators looking to maintain character consistency. Minimum 24GB VRAM required. Boost your Flux workflow with custom LoRA models today!

If You Like tutorial like this, You Can Support Our Work In Patreon:

#FluxAI #LoRATraining #AIArt #ComfyUI #MachineLearning

[kalakala]

Omg! This model develop so fast! Just launched CN, Lora training are ready.

[basemmgtow]

is there any chance i can do that with 12 vram?

[openurwindows]

I also have a 4070 Ti Super 16GB, so I'm curious about the benefits.

[pastuh]

Why would you resize the images if the LoRA trainer is supposed to resize them automatically?

[Beauty.and.FashionPhotographer]

what was used to to your final animation, image to video, where she walks ?

[ojikutu]

Thanks. Good work. AI-ToolKit repo is not in your description, would have been helpful.

[CyberPhonkMusic]

I did LORa training for FLUX, when I put more than one person in the image, it duplicates the LORA faces in all the characters that appear in the image, what can I do to avoid duplicating the faces of the LORA training?

[daetojekf]

Comfy refuses to apply my lore as if ignoring it, I do like your video 1v1

[yngeneer]

yeah, exactly, what if I have 16gb vram + bios enabled ram share with vram another 32bg, so totally 48gb? does that count as a 48gb vram?

[timothywells]

Thanks I've been wanting to try a flux lora locally after trying for weeks to train a character lora in sdxl without much success. In sdxl when I use the loras each picture has elements of the original reference images but doesn't really look like the character. And this is even at 10000+ steps and prodigy set to LR of 1 😔

[crazyleafdesignweb]

Very nice, and fast release a Lora Training.

[UnchartedWorlds]

Flux Capacitor!!!! Benji where we are going we won't need capacitors!!!

[massibob]

Good job man !
Do you know how to setup the yaml to use 2 same graphic cards ? SO I will have device 0 and Device 1.

[pastuh]

Are you going to fine-tune the model?
A tutorial would be helpful :)

[jonjoni]

i find it impossible to download the models. it starts downloading the model at 30mb/s and then it goes down to just a few Kbytes and stays at 99%. i have tried with different hugginface tokens (write, read finegrain....). i also leave the .yaml by default except the path where i indicate the directory of my dataset. by the way i have a 14900k 4090 and 128ram and windows 11

[FJKMIsotryFitiavanaSiteWeb]

what if I already have the models tensor locally, and don't want to download them again from HuggingFace

[kallamamran]

Why two different captioning methods? 🤔

[RagonTheHitman]

Why should I train "private" and LOCAL on my PC ... if Huggingface/BlackForestLabs get's my data anyways and knows everything.... And I think, I must be online for training (to start). ?!

[jonjoni]

Me resulta imposible descargar los modelos. comienza a descargar el modelo a 30 mb/s y luego baja a solo unos pocos Kbytes y se queda en el 99%. He probado con diferentes tokens de Hugginface (escribir, leer finegrain....). También dejo el .yaml por defecto excepto la ruta donde indico el directorio de mi conjunto de datos. Por cierto, tengo un 14900K, 4090 y 128RAM y Windows 11

[Point.Aveugle]

Please Kohya next, they 've got it having good results with 500 steps. All my loras have been good (way better than sdxl and pony) with default settings using ai-toolkit but they take hours to go to 2000-3000 steps. As someone mentioned below fiddle with high weights, 1.5-2 have worked for me. Also comment out most of those samples when training, they take unnecessarily long. I want to bump up learning rate but not sure how high to go; I read somewhere that people have been using 4-e4 but I tried 1-e3 and it wen crazy after 500 steps so I was thinking even that would be too high.