Dragon Ball Super style LoRA
Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
Trained this from screens taken from Dragon Ball Super and Super Hero (just to be able to use the Gohan's SSj Beast). It can't do Namekians and other races too well, probably because of the base model. It should be able with a dedicated model (like a Namekian LoRA).
Keep in mind this is a style LoRA, meaning it can get close to character but it's not aiming at doing them without a dedicated character LoRA/embedding. This one is mainly targeted at people who wanto to make their own OC.
Should be used at around 1 weight using AnyLoRA with trigger dbsuper style to improve the style.
How to use LoRA's in auto1111:
Update webui (use
git pulllike here or redownload it)Copy the file to
stable-diffusion-webui/models/loraSelect your LoRA like in this video
Make sure to change the weight (by default it's
:1)
Description
FAQ
Comments (9)
Looks better than super itself lol
I excluded trash screens ahah
ty for this bro
By the way, where is R-ESRGAN AnimeVideo?
Will you also make a Z version?
RIP Toriyama!
whats the trigger word and the recommended wight????
I’m doing something wrong. I’ve never gotten a solid black image before until I used this LoRa. I’ve got this Lora plus a character lora and the right prompts but each time I click run it will spit out a solid black image with nothing there. When I don’t use this lora the problem goes away.
Whats the trigger word? And the AnyLoRa checkpoint needs a bid, what can I use instead?