Home
Creators
Search Recent Random
Posts
Search DMs Popular Hash Lookup Tags Random
Importer
Import FAQ
Register Favorites Keys Review DMs Logout
Community
Telegram ThePornDude
Home Creators Posts Import Register Favorites Logout

Extracted LoRA Quick Test (Patreon)

Published:
2024-07-23 00:01:09
Edited:
2024-07-23 00:07:11
Imported:
2026-06

Content

I did a test for one of our supporters. Used one of my older quite a bit overtrained DreamBooth modelExtracted LoRA as you can see yields almost perfect quality. Yes subtly changed but you can get quality with more generations

 

Files

Comments

Manpreet Singh

Can you extract LORA directly from training images somehow? Instead of training a model first, then extracting LORA from that like you did? (If my understanding of what you did is correct)

Sipriyani

do we have to use our own extracted loras, with the base safenetors? (for your instance, Realvisionxl4)

Josh Tech

I am extremely satisfied with the results of the Dreambooth models. However, I see a reason that speaks for an extracted Lora: Even if I use all regularization images, I perceive that other object classes are influenced by the training content. So men always look a bit like me. Even women have a subtle resemblance to me in their facial features. Presumably this problem could be avoided with a Lora, right?

Nedo Braun

Thanx for this Information! I will check this tonight. What i did is this if my LoRA extraction is not good enough as the full fintetuned model, i create a picture with the LoRA, then send the pic to IMG2IMG, inpaint, and mask the face there AND (important) use the Full Fintetuned Modell. - The Result is incredible

Nedo Braun

i have one question tho, in your lora extract config you use CPU for loading the models and save/load precission to float. I have a 4090 should i use instead Cuda and bf16 ?