BETA:
I completely changed the tags and the dataset balance.
In this version my LoRA should be way more stable and should adapt well with more models than before.
Changes in this version:
Now you can let Charlie wear the red jacket typing in the prompt "red jacket"
Using "charlie morningstar" you will generate standard Charlie
Using "charliedemonic" you will generate demonic Charlie (still unstable)
Alpha (OLD VERSION):
My first experiment with a non "human" LoRA.
First version.
Trigger Word: Charlie Morning star (without trigger will appear less cartoonish)
I'm not satisfied yet with this version.
With some prompts you should increase the weight of the trigger words to retain more facial features.
Description
Trained on 40 selected images from the Amazon Prime Show.
FAQ
Comments (4)
I'd pay 50 grand for a lora like this
We are too used to low-quality LoRA 🤣
Could've tagged it "red suit" to be more accurate. I also would've tagged the "black bowtie" and "white collared shirt" underneath, but different LoRA dataset preparation workflows, I suppose.
I may try to change the tags that way and see if the result changes. I'll update in the next days the LoRA if i can :)
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.