Wes Anderson 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 on AbsoluteReality, I noticed that the base model understands the prompt wesanderson which is also the trigger, probably due to SD1.5 having his works in the dataset. Anyway this lora bumps the style up quite a bit and also helps to increase the realism.
I had a lot of fun using it. Should work around weight 1 on my model.
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
:1which is usually too high)
Description
FAQ
Comments (1)
This LORA doesn't achieve Wes Anderson's iconic style very well. Here are some prompt phrases I have used without this LORA to get closer to Wes Anderson's style.
Positive Prompt:
Brightly Lit, Highly Visible
Vibrant Colors, Pastel Hues
Analog Style, Kodak Max 400 Film
20mm f/1.8 lens, Wide Angle Shot.
Symmetrical Composition
Whimsical yet Numb.
Quirky Character Designs
Dollhouse Aesthetics
Negative Prompt:
(normal negative keywords), details, clutter, left offset, right offset, HDR, details, pose, expressions
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.