Making models can be expensive. Do you like what I do? Consider supporting me on Patreon 🅿️ or feel free to buy me a coffee ☕
A while ago I hosted a lecture on LoRA training. To demonstrate, I made a Phoenix lora with crappy Adobe Stock images, even with the watermark still there.
I made sure to tag most of the things in the example, as usual with my LoRA trainings, so not only this LoRA learned how to make a "midjourney style" Phoenix but, when used on anime models with any prompt, it makes a very cool style.
Use it on DreamShaper to make cool looking fire birds, or with any other model to add some vibrant style.
Go wild with it.
(Disclaimer: since this was trained on adobe stock, make sure you have watermark
as negative prompt)
How to use LoRA's in auto1111:
Update webui (use git pull
like here or redownload it)
Copy the file to stable-diffusion-webui/models/lora
Select your LoRA like in this video
Make sure to change the weight (by default it's :1
)