NokiMo
Innovate Futures @ Benji
Innovate Futures @ Benji

patreon


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

Tutorial Guide : https://youtu.be/F-7gfqSP2ZY

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

Install Ollama with ComfyUI : https://youtu.be/EQZWyn9eCFE

Create AI Video Scenes And Characters : https://youtu.be/BPrLS59dUtE

Github Project - Ostris/Ai-Toolkit : https://github.com/ostris/ai-toolkit

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.

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!

Comments

Now the LORA dataset FLORENCE save it as 0,1,2,3,4 txt. Cannot get the filename and save it near each JPG the TXT as the same filename?

Valics Lehel

Have you try again after this? Looks like their server having problem.

Benjamin Law

First of all the type of token I created in HF is write type and as for the .env file, I didn't name it just .env so that the content was the following and had no spaces (the token has already been removed don't worry): HF_TOKEN=hf_OkTZWWdXIlZodvZbpVsDrfVSlCtgUJHFVVVs.

jonathan sanchez

How did you get to even download the models? I renamed a txt file to .env and copied in my hf access key and all I get is "is not a valid model listed on huggingface.co" and please pass a valid token. I don't understand what I'm doing wrong? I already have the models downloaded is there anyway to just use those?

Error_404_unknown

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

jonathan sanchez


Related Creators