Join the Galactic Empire and help us bring peace to the galaxy!
Use this model to turn pretty much anything into a white shiny sci-fi version of that thing with small black details. Make the emperor proud!
Usage
Use the trigger word: "TheEmpireStyle, white," along with the LoRA to activate it.
This LoRA supports RGB color changes a little bit, so you can replace the word "white" with another color. But the results will be best with white. You can try to increase the weight of the color to force the effect in there more.
Example prompt:
TheEmpireStyle, white, cat, hi-tech plastic <lora:TheEmpireStyle:1>
LoRA weight, sampler, steps and CFG scale: Whatever, it seems to handle anything I throw at it. Go nuts!
Tips and tricks
It's not needed, but using some of the words from the list below can enhance the effect. Feel free to add them to your promptings.
hi-tech plastic
sci-fi design
retro futuristicNow with training data attached!
Like it?
Description
FAQ
Comments (10)
The safest car in the galaxy.
I can't believe I'm going to download this, but dammit, I love it. 😆
this. is. hillarious ! :) :) :)
This looks genius! Thank you so much for making this and sharing it! This resource should be used by product designers to make some brilliant designs. My current PC actually looks like it was designed by this lora, and I love it. :)
Cheers! Yeah I agree. However, the designs are inspired by the original designs, and that's where the true genius is. It's both timeless and elegant. I feel like I managed to capture it well in this model.
Is it wrong to want to live in a house where this LoRA decorated everything?
@mnemic You did a great job it seems. I'm looking forward to trying this out.
I say this technique WILL be used widely by designers everywhere in near future. It's a fantastic tool.
Anyone have tips for applying this lora to img2img? TIA.
I tried it a little bit this model and it kind of works.
But it's not like it automatically applies a Stormtrooper uniform to a person.
It wasn't trained on a single image of a stormtrooper. Just the aesthetics of their style.
I tried it with a human, a mushroom and a dog.
I used 1.5 model weight, and 1.3 activation keyword weight.
Good luck!
@mnemic i was actually trying it with a doggo and couldn't get it to apply even a white color, what model did you use? And thanks again for the reply and for looking into it! You rock!
@Pity_the_Foo Here are the settings I used:
<lora:TheEmpireStyle:1.5> (TheEmpireStyle:1.3), (white:1.5), (robotic dog wearing hi-tech plastic armor:1.4), in front of a red wooden wall, (Masterpiece:1.3) (best quality:1.2) (high quality:1.1), edgQuality
Negative prompt: watermark, low quality, ugly, blurry, lowres, bad hand, blurry eye, extra legs,malformed limbs,disappearing legs,poorly drawn hands,worst quality,cloned face,cropped,malformed,missing fingers,mutated, UnrealisticDream,BadDream,EasyNegativeV2
Steps: 40, Sampler: Euler a, CFG scale: 7, Seed: 1121974513, Size: 512x1112, Model hash: 4199bcdd14, Model: revAnimated_v122, VAE hash: f921fb3f29, VAE: RandoMix3.vae.pt, Denoising strength: 1, Clip skip: 2, ENSD: 31337, ControlNet 0: "Module: depth_midas, Model: control_sd15_depth [fef5e48e], Weight: 0.8, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced", ControlNet 1: "Module: canny, Model: control_sd15_canny [fef5e48e], Weight: 1, Resize Mode: Crop and Resize, Low Vram: False, Processor Res: 512, Threshold A: 100, Threshold B: 200, Guidance Start: 0, Guidance End: 1, Pixel Perfect: False, Control Mode: Balanced", Lora hashes: "TheEmpireStyle: 8b529fad3844", TI hashes: "edgQuality: 16feb3a76c29, UnrealisticDream: a77451e7ea07, BadDream: 758aac443515, EasyNegativeV2: 339cc9210f70", Version: v1.6.0
As you can see, I had to raise the weights a bit on the trigger words.
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.