How to fine tune it?

#35

by AeroDEmi - opened May 15

May 15

I was wondering if it is possible to fine-tune the base model, or how to create similar Loras. Can we use the same diffusers text2img examples ?

Yanzuo

ByteDance org May 15

Hi, @AeroDEmi
Of course. You can directly download and load our models into training.
Try merge it into UNet and create a new LoRA, or just fine-tune our LoRA. Both are worthy a try.
Our models are fully publicly available.

AeroDEmi

May 15

Awesome! Any details on how you tuned them? Should I use the LCM guide?

Yanzuo

ByteDance org May 16

Hi, @AeroDEmi
We haven't try further fine-tuning them. You could give it a try.
It should be working just by merging the LoRA into UNet and treat it as a new accelerated base model.

AeroDEmi

May 17

•

edited May 21

Cool! Will do!

AeroDEmi changed discussion status to closed May 21

Watarungurunnn

Aug 1

@AeroDEmi
Hello. Thank you for your valuable discussion. Did you make it happen? If so, could you share some example code with me?

Adenialzz

Oct 9

how hyper sd/flux trained? Could you please provide a fine-tune script? thanks

Upload images, audio, and videos by dragging in the text input, pasting, or clicking here.

Tap or paste here to upload images

· Sign up or log in to comment