Comment on How to Create Art for a Book?
lefthandeddude@lemmy.dbzer0.com 5 days agoThat sounds so hard to do locally. I don’t even know where I would begin. Is that expert level stable diffusion?
Comment on How to Create Art for a Book?
lefthandeddude@lemmy.dbzer0.com 5 days agoThat sounds so hard to do locally. I don’t even know where I would begin. Is that expert level stable diffusion?
Even_Adder@lemmy.dbzer0.com 5 days ago
You would probably need to use something like Visual Novel Character Creation Suite to generate a character and a dataset for LoRA training, and then train a LoRA for each character.
If you’re trying to get started with generating locally, here’s a tutorial for Comfy UI.
scrubbles@poptalk.scrubbles.tech 5 days ago
A big note that it’s nigh impossible to put two separate characters in one image, as the model has no idea who you are referencing. You can see this in all image models how they usually only have one central person, or two people who look oddly alike. Only way to get two or more characters would be with complex workflows to inpaint certain characters.
Even_Adder@lemmy.dbzer0.com 4 days ago
Yeah, if you’re using character LoRAs you’re probably going to need to use regional prompting to keep the concepts from leaking into each other.