How to Train a Flux LoRA Locally in 15 Minutes! Create an AI Influencer with ComfyUI Workflows.
Added 2024-12-20 19:16:30 +0000 UTCIn 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
Comments
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.
Joel
2025-03-13 02:19:30 +0000 UTCthis helped! Thanks for the link bruno!
Jeff Merilo
2025-02-26 08:47:40 +0000 UTCMy workflows are dependent with studio
DigitAll
2025-02-16 07:02:26 +0000 UTCi 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.
Joe C
2025-02-16 00:34:47 +0000 UTCIt works, I did the manual installation step by step and it works. follow what is written I'll link you a video where it explains. https://www.youtube.com/watch?v=nY5qsifYr_8&t=638s
bruno davi
2025-02-06 22:31:49 +0000 UTCin 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.
bruno davi
2025-02-06 22:26:24 +0000 UTCDid you figure this out? I'm having the same problem.
Landrodis
2025-02-06 14:47:52 +0000 UTCWhen I press to make captions
bruno davi
2025-02-05 12:33:10 +0000 UTCHi, 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
2025-02-05 12:30:13 +0000 UTCyes for face use a closeup photo. only face no body.
DigitAll
2025-01-27 11:36:29 +0000 UTCHey 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?
Eusthace
2025-01-27 10:37:58 +0000 UTCmaybe https://huggingface.co/openfree/flux-lora-korea-palace?utm_source then i think can edit it in the root folder called models.yaml
gary
2025-01-06 14:17:21 +0000 UTCHi. Text lora. I think not.
DigitAll
2025-01-02 16:51:34 +0000 UTCHello, 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.
재선 하
2025-01-02 16:48:37 +0000 UTCI think This video will be get more subscribers to you 🔥
Miriyala Praveen Kumar
2024-12-20 19:20:19 +0000 UTC
