Furkan Gözükara
patreon
SECourses 3D Render for FLUX LoRA Model Published on CivitAI - Style Consistency Achieved - Full Workflow Shared on Hugging Face With Results of Experiments - Last Image Is Used Dataset
🕑 Added 2024-09-08 00:11:27 +0000 UTC
CivitAI Link : https://civitai.com/models/731347
Hugging Face Link : https://huggingface.co/MonsterMMORPG/3D-Cartoon-Style-FLUX
SECourses 3D Render for FLUX LoRA Model Published on CivitAI - Style Consistency Achieved - Full Workflow Shared on Hugging Face With Results of Experiments - Last Image Is Used Dataset
Comments
Furkan Gözükara
it provides info regarding how overfit model is, how destroyed its capability and generalization is
努力生活的超子
Hello, I saw your Flux style training tutorial on civitai. When I see the grid results I have a question, why are you testing the following prompts [ "a ohwx render of car" ] and [ "a ohwx car" and "a ohwx style car image"] and ["a car rendered in ohwx 3d car"], What is the purpose of testing these prompts?
Furkan Gözükara
i used same. LR changes when you use multiple GPUs
Jonathan Streeter
Should we use the same learning rate for style training as for character training?
Furkan Gözükara
nope but if you have a project budget i can do research for you
BGM
Hello, have you tested the Lora training parameters for interior architectural styles? I've been failing at training.
Furkan Gözükara
sure let me know the results
jonathan sanchez
hey furkan, i just read it now. i will tell my partners (there are 4 of us). although for the moment we have limited capital (for the moment we have raised 40% of the investment we want). but i would love to be able to count on your knowledge.
Furkan Gözükara
thank you hopefully more to come
Furkan Gözükara
well if you have a budget i can do consultation and research
George Gostyshev
Great job done! Appreciated for making style training and not person!
jonathan sanchez
great, I'm looking forward to seeing it
jonathan sanchez
thank you very much, now i will see it. i have an AI fashion startup and we work with several brands some very important and i can't use many loras in the same flow because it damages the image. we need to train people, clothes, and a neutral gray background in the same lora to do the shooting for the ecommerce
Furkan Gözükara
yes it is my this week research hopefully
Furkan Gözükara
in this video i explain multi concept logic with repeating : https://youtu.be/nySGu12Y05k you dont need reg images. it is not difference than sdxl but flux much more powerful and robust
jonathan sanchez
is there any possibility of making a dreambooth in flux at the moment?
jonathan sanchez
hey furkan! do you know where there is information to train several concepts in the same lora for flux? is it different from how it is done in sd xl? do you need regularization images? i want to train several clothing items, several characters and a neutral gray background of ecommerce.
