Home Creators Posts Import Register Favorites Logout

Downloads

Content

In this video, learn how to train a Flux LoRA locally in just 15 minutes! We’ll walk you through the process of using ComfyUI workflows to create an AI influencer and train your own custom LoRA model. Perfect for beginners and advanced users alike!Download FluxGym and Workflows: https://www.patreon.com/posts/comfyui-studio-111135526

Files

How to Train a Flux LoRA Locally in 15 Minutes! Create an AI Influencer with ComfyUI Workflows.

In this video, learn how to train a Flux LoRA locally in just 15 minutes! We’ll walk you through the process of using ComfyUI workflows to create an AI influencer and train your own custom LoRA model. Perfect for beginners and advanced users alike! To install FluxGym you must have "Git" and "Python" installed on windows. I used RTX 3090 for lora training. Minimum Hardware Requirements for "ComfyUI Studio": - 6-core CPU, 3GHz - 32GB RAM - 250GB HDD - Nvidia video card, RTX 2060 12GB VRAM or higher (only Nvidia) - Windows 10/11 (only windows) 👉 DOWNLOAD: "ComfyUI Studio" with preinstalled 150+ workflows (30GB, no installation required). https://www.patreon.com/posts/comfyui-studio-111135526 - Free Epic ComfyUI workflow Pack: https://www.patreon.com/posts/free-epic-pack-109921956? Don't forget to like, subscribe, and stay tuned for more updates! "ComfyUI Studio" is an independent project that uses the open-source ComfyUI platform to create custom workflows. #ComfyUIStudio #IDWorkflow #AIArt #DigitalPortraits #PortraitWorkflow #controlnet #depthmap #workflow #pose #comfyui #faceswap #facefix #flux #forge #sd #stablediffusion #sd3 @tutorial #install #instandid #flux How to create illusion photos

Comments

Perilla(들깨)

Hello, I was wondering if there is a way to train Flux LoRA locally to enable Korean text as LoRA? I was wondering if you could help me with this.

Eusthace

Hey everyone, great to be part of this community! I'm new here and trying out Character v3 for the first time. I’ve noticed that the generated character looks quite different from the real person in the photo. Is there a specific parameter I can adjust to make it more accurate?

ComfyUI Studio

yes for face use a closeup photo. only face no body.

bruno davi

Hi, I was trying Fluxgym but I have this error: Unable to create tensor, you should probably activate padding with 'padding=True' to have batched tensors with the same length. I'm following your video.

bruno davi

When I press to make captions

Landrodis

Did you figure this out? I'm having the same problem.

bruno davi

in the insto trying with manual installation, because then in the interface it has the possibility to work with 20/16/12 vram, so it must work. https://github.com/cocktailpeanut/fluxgym as soon as it's ready I'll let you know if it works.

Joe C

i have a question. if I sign up am I able to get the workflows without downloading and installing comfy UI studio? I'm using comfy UI desktop and I like using that for now.

Jeff Merilo

this helped! Thanks for the link bruno!

Joel

I also got the same error when installing. I originally had done the manual install before trying this, but when you hit to train your LoRA, the model starts downloading and errors out for me after about half the download is done. I've been trying to fix this for a few days now.