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
it provides info regarding how overfit model is, how destroyed its capability and generalization is
Furkan Gözükara
2024-09-11 12:22:59 +0000 UTCHello, 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?
努力生活的超子
2024-09-11 10:38:08 +0000 UTCi used same. LR changes when you use multiple GPUs
Furkan Gözükara
2024-09-10 16:54:49 +0000 UTCShould we use the same learning rate for style training as for character training?
Jonathan Streeter
2024-09-10 16:00:42 +0000 UTCnope but if you have a project budget i can do research for you
Furkan Gözükara
2024-09-09 14:02:58 +0000 UTCHello, have you tested the Lora training parameters for interior architectural styles? I've been failing at training.
BGM
2024-09-09 13:18:41 +0000 UTCsure let me know the results
Furkan Gözükara
2024-09-09 10:20:13 +0000 UTChey 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.
jonathan sanchez
2024-09-09 06:28:12 +0000 UTCthank you hopefully more to come
Furkan Gözükara
2024-09-08 15:30:12 +0000 UTCwell if you have a budget i can do consultation and research
Furkan Gözükara
2024-09-08 15:30:05 +0000 UTCGreat job done! Appreciated for making style training and not person!
George Gostyshev
2024-09-08 12:53:19 +0000 UTCgreat, I'm looking forward to seeing it
jonathan sanchez
2024-09-08 11:57:41 +0000 UTCthank 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
jonathan sanchez
2024-09-08 11:57:19 +0000 UTCyes it is my this week research hopefully
Furkan Gözükara
2024-09-08 11:46:01 +0000 UTCin 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
Furkan Gözükara
2024-09-08 11:45:52 +0000 UTCis there any possibility of making a dreambooth in flux at the moment?
jonathan sanchez
2024-09-08 10:20:44 +0000 UTChey 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.
jonathan sanchez
2024-09-08 09:54:35 +0000 UTC
