NEXT PATREON EXCLUSIVE LORA
Added 2023-10-12 16:22:32 +0000 UTCComments
I already made a video on lora style training: https://youtu.be/1BCYdd9r1To the principle always stays the same
Aitrepreneur
2024-10-31 10:53:16 +0000 UTCHi! What would I use to create a LoRA for my own Artworks? The shaopes are never always the same like a LoRA object, but they do have a style like a LorA style, i'm not really sure what to choose! : )
gabbatv
2024-10-31 09:24:19 +0000 UTCCan you make a lora of Elle Fanning?
Liam
2024-02-07 05:10:49 +0000 UTCIt worked perfect, thank you!
Víctor Ahumada
2024-01-20 21:06:04 +0000 UTCyes but the best way to do this is with inpainting
Aitrepreneur
2024-01-19 22:00:10 +0000 UTCHello, I just saw your object training video in SD. I have a question. Can you combine an already created character LORA with an object LORA? Like for example adding a ring to an existing LORA?
Víctor Ahumada
2024-01-19 20:10:07 +0000 UTCStylised Cartoon Character
2024-01-15 10:10:23 +0000 UTCCartoon character
2024-01-08 13:31:24 +0000 UTCHairstyles
ZenzeosArt
2023-10-28 16:43:34 +0000 UTCComfyUI tutorial with instant LoRA please
2023-10-26 01:30:51 +0000 UTCControlnet for SDXL tutorial for AUTO1111 please
2023-10-26 01:30:33 +0000 UTCA handheld object like a sword would be sweet.
Jan-Michael Losada
2023-10-25 22:03:35 +0000 UTCI think 'concepts' would be interesting. Things like lighting, extra detail, de-aging, fixing hands etc...
2023-10-25 17:12:25 +0000 UTCyes or a particular mask
Phillip Gimmi
2023-10-24 22:40:28 +0000 UTCsend me some more info in dm
Aitrepreneur
2023-10-23 17:49:05 +0000 UTCI tried to train a specific bag in a shape of a vegetable and somehow this didn’t work at all, would love to see how you would do it! Character even if they are very abstract works great for me (sdxl rtx 4090)
Paula Kühn
2023-10-22 21:23:07 +0000 UTCnot really, reg are optional, they can make the model better but you can train one without them
Aitrepreneur
2023-10-19 08:54:26 +0000 UTCI see. Then you have to get a bunch of Regularization images I guess?
2023-10-18 19:46:44 +0000 UTCwell it's the same principle as when you want to train a person, except you use the race of dog or cat for the token. So if your dog is a german shepherd, you will simply put "german shepherd" for the instance prompt and "dog" for the class prompt, simple as that :)
Aitrepreneur
2023-10-18 16:36:16 +0000 UTCWould be nice to learn how to train a Lora on a specific dog or cat so you can put your animal in any picture / settings you want :)
2023-10-18 14:30:27 +0000 UTCit doesn't work like that, correct hand generation is a big issue for most ai models, training a small lora is not gonna fix that, we'll probably have to wait for the next few SD base models for it to improve
Aitrepreneur
2023-10-16 12:26:04 +0000 UTCobject training is probably gonna be my next video :)
Aitrepreneur
2023-10-16 12:24:49 +0000 UTCVector design (Logo style)
2023-10-16 05:16:22 +0000 UTCOr hand an object such as a handbag from one character to another and have that second character carry it in future generations.
Hadriex
2023-10-16 04:11:38 +0000 UTCAny chances to get a proper training LORA for mutated hands, legs and etc? It'll be sooo much appreciated by whole community of SDXL users.
George Gostyshev
2023-10-15 10:07:11 +0000 UTCFor me it would be very interesting to find out how to train objects that interact with a model, e.g. a chair you are sitting on. Or how to add more datasets to an already trained Lora, i.e. how to resume the training. Thank you.
2023-10-15 07:33:16 +0000 UTCoh but for this current poll: would love a pose lora of people taking a selfie :D the best would be a combination of a 3rd person view and the actual selfie that was taken .. but that is quite a lot to ask haha
cblomert
2023-10-15 01:06:51 +0000 UTCto be honest - i don't feel i need the exclusive loras - i don't know how the other patreons feel, but if it takes a bunch of time and effort - i would say skip them- and rather poll us for general topics for you to explore and explain to us :D for one: i would love to learn a bit more about the current state of 'local' LLMs and how to finetune them much love <3
cblomert
2023-10-15 01:02:46 +0000 UTCObjects is so essential, we have so many styles already
2023-10-14 14:31:30 +0000 UTCposes
CJ
2023-10-14 09:26:27 +0000 UTCA lora is not gonna fix that, it's an issue with most Ai models unfortunately :/
Aitrepreneur
2023-10-13 11:12:10 +0000 UTCObjects like holding items would be verrryy useful. Currently making a space marine Lora but hands and weapons often get messed up.
2023-10-13 07:29:11 +0000 UTCpose
shen oracle
2023-10-13 01:58:12 +0000 UTCvector design!
2023-10-13 01:52:34 +0000 UTCHands or teeth. It's amazing how hard it is to get either right.
2023-10-12 23:41:42 +0000 UTCarchitecture
Mahmoud Alhashim
2023-10-12 19:21:40 +0000 UTCin the spirit of Halloween which approach would be best to make a Lora to apply make up effects on someone like witches noses, vampire teeth, elf ears, etc.?
2023-10-12 17:02:04 +0000 UTCImo styles are best because we can use them the most flexibly
Charles Marsh
2023-10-12 16:53:03 +0000 UTC