Cyberpunk Style
This is a cyberpunk style LoRA. That's it.
Unlike a certain game, this LoRA doesn't overpromise and underdeliver.
More like seedy project red, right?
Why 2 Cyberpunk models?
I also have a "Cyberpunk World" model. They are both trained from the same data. The only difference is the trigger keyword. This one uses a made-up word which should make the training more pure and it should inherit less knowledge about what cyberpunk means, outside of the training data. The other one uses the actual word of "Cyberpunk Style" in it, so it "inherits" information about this from the base model you're using. In theory at least. Both models have the same prompt and seed as their showcase images, so you can compare and pick your favorite, or use them both for all I care! I'm not your parent!
It may be that the other model is slightly better at making humans. Neither LoRA has ever seen a human or a cyberpunk human, but if the other model's training data is merged with "generic" cyberpunk human training data, there may be more human-skinned people in that one. This one on the other hand I feel produce more creative and inventive results.
There's also an older "0.5-version" of this model. This one is fully trained, but the results are a bit less colorful and a bit more foggy/washed out with some models. I ended up re-training, but this version is still good, so I decided to share it as well.
Usage
Use the trigger word: "C7b3rp0nkStyle" along with the LoRA to activate it.
Example prompt: C7b3rp0nkStyle computer mouse <lora:C7b3rp0nkStyle:1>
I've found that most settings work well with this model. No special samplers or CFG-scale.
Tips and tricks
Here's a list of keywords you can use to enhance the different effects of the model.
cyberpunk style
colorful
glowing
color explosion
hi-tech
sci-fiLike it?
Description
This was an earlier test version of the model. It turned out too dull and lacked contrast, so I increased it on most of the training images for better results.
In case someone wants to try this version, I figured I'd post it.
With some photorealistic models, it still looks very good!
FAQ
Comments (8)
Thank you for these two LoRAs! I'll certainly test their limits. That would be great if you have time and make the image order same for both LoRAs for users easily compare the results.
It is the same for all images except the first 2. I just love that damn shark so much I had to put it as #1 :D
But the rest should be the same if you open it up in a tab each.
I also have tons of comparison sheets I can post. I'll drop a few below.
@CGArtist Open them up in a new browser window to see them full-sized.
is this a duplicate of:
https://civitai.com/models/156182/cyberpunk-world ?
Kinda. They have different trigger words but that's if from what I'm seeing. Probably should have them under the same model entry, just as different "versions" instead
Kind of, but they produce different results.
There's an explanation in the model description.
It's not a bad idea to merge them into one, I may do that.
so looking at both i se how they were effected at least in theory. guess what, so i was testing trigger word setups sedt makes a different image then deswq and throw i one letter on and it changes again. so my point. the weight of the prompt has changed by the change of letters (token thingie stuff )
any variable can shift the image, so crazy : ) thanks for all the work
and that was testing letters put together connected to nothing but token weight
Yeah, random be randoming.
Such small variations create such different results in the end!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.