Quick Generate
Select a style, write what you want to see and click Generate
What you want in the image.
Clear
Random
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting

Model Description by Creator

Introducing Terran Tech! My first published model. I've been trying to learn as much as I can about the art of building data sets. I know that this has been done before, but now i'm making my own stab at it. Maybe we'll see others try the same in the future!

This theme has sort of been my lab. I trained this with kohya's scripts, the gui version of the project. This attempt was the first i did with an image set larger than 100. 243 images. Collected from game assets, concept art, fan creations. Portraits, units, buildings, cinematics, cosplays, anything that reflected the terran aesthetic and lifestyle, i tried to incorporate into the set.

Prompting was experimental as well. I normally for trying a style out, I'd caption simple like "sks car" much like Kony's tutorial teaches. I want to expand my captioning game though so this is more robustly captioned. All manually. some is descriptive and some is for flavor. I didn't focus too much on starcraft accurate names and descriptors, since this was meant to apply generally. A future version i may do longer captions, clip interrogations added, more flavor, and more SC accurate tagging.

My goal was to generalize the model so that it could appeal to a lot of different prompting styles and provide a lot of surprising variety. All sample images are generated with a webui extension, one button prompt. This was to remove any bias i personally might inject into my prompting. I merely added "T3rran Engineer" and interesting background. Backgrounds tend to be flat without a descriptor. easynegative was used for the negative prompt.

t3rran is the strongest keyword here. Examine the metadata to see how else i tagged it. Some of the flavor in the captions are neat. Renegade, void, phantom, medic, support, upgraded. Try it and see. I really have no idea what i'm doing here, but this appears to work so i'm publishing. If anyone has any tips then please feel free to fire them my way.

I want to thank anyone whose ever produced a guide or anyone whose ever answered questions on discord servers. I've probably looked at a little of all of them out there in the last few months, and i've been asking as many questions as i wrap my head around. The help has been invaluable.

Credit to Blizzard Entertainment for creating all the wonderful aesthetics I'm trying to incorporate. Since I don't have the rights to authorize commercial use of Blizzard's IP, I've set those rights as none. This is not a personal choice but rather a matter of fact that should be recognized.


Images Generated With This Model

AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
<lora:TerranTech R1:0.7> RAW Photography of a (t3rran:0.9) combat marine, blue steel, 8k 4k resolution, full portrait, heavy canons, cinematic,  (detailed visor:1.1),  lowkey, molten lava battlefield, volcano region, natural lighting, digital photo
N/A
Hidden For Public Users
<lora:TerranTech R1:0.7> RAW Photography of a (t3rran:0.9) combat marine, blue steel, 8k 4k resolution, full portrait, heavy canons, cinematic, (detailed visor:1.1), lowkey, molten lava battlefield, volcano region, natural lighting, digital photo
<lora:TerranTech R1:1.1> t3rran barbeque, detailed
N/A
Hidden For Public Users
<lora:TerranTech R1:1.1> t3rran barbeque, detailed
<lora:TerranTech R1:1> t3rran portrait,, wall Graffiti,  ,close up of a Boorish Warlike The City of El Dorado, at Golden hour, Masterpiece, Post-Punk, hair light, octane engine, 64K, interesting background
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran portrait,, wall Graffiti, ,close up of a Boorish Warlike The City of El Dorado, at Golden hour, Masterpiece, Post-Punk, hair light, octane engine, 64K, interesting background
<lora:TerranTech R1:1.35> t3rran coffee maker machine, detailed
N/A
Hidden For Public Users
<lora:TerranTech R1:1.35> t3rran coffee maker machine, detailed
AI Model Training

Create Your Own AI Model

Train AI to generate stunning photos of yourself in any style or setting
<lora:TerranTech R1:0.85> RAW Photography of a (t3rran:0.9) unit, spider mech, red steel, 8k 4k resolution, cool colors,    cinematic,  (extremely detailed glass visor:1.1),  lowkey,  factory background, studio lighting, digital photo, phantom void style
N/A
Hidden For Public Users
<lora:TerranTech R1:0.85> RAW Photography of a (t3rran:0.9) unit, spider mech, red steel, 8k 4k resolution, cool colors, cinematic, (extremely detailed glass visor:1.1), lowkey, factory background, studio lighting, digital photo, phantom void style
<lora:TerranTech R1:1> t3rran, (art by Steven Klein:0.8), (art by Julie Blackmon:0.8), cowboy shot, cinematic of a Tangible  spider mech, glass cockpit, deep focus, weirdcore, volumetric lighting, anaglyph filter, contest winner, interesting background
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran, (art by Steven Klein:0.8), (art by Julie Blackmon:0.8), cowboy shot, cinematic of a Tangible spider mech, glass cockpit, deep focus, weirdcore, volumetric lighting, anaglyph filter, contest winner, interesting background
<lora:TerranTech R1:1> t3rran engineering, (art by Theodore Robinson:0.7), (art by OSGEMEOS:1.2), (art by Irving Penn:0.7),  landscape of a Mean The Olympian Home of the Gods  and Lamborghini, at Twilight, Simple illustration, waning light, interesting background
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran engineering, (art by Theodore Robinson:0.7), (art by OSGEMEOS:1.2), (art by Irving Penn:0.7), landscape of a Mean The Olympian Home of the Gods and Lamborghini, at Twilight, Simple illustration, waning light, interesting background
<lora:TerranTech R1:1> t3rran, Gigantic spider mech, machine with hardened glass, cowboy shot, cinematic lighting
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran, Gigantic spider mech, machine with hardened glass, cowboy shot, cinematic lighting
<lora:TerranTech R1:1> t3rran engineering, Renderman, Pencil painting, Fractal,  landscape of a Deteriorating The Mesa Verde, Snowy, Single Color, (art by Matt Groening:1.1), interesting background
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran engineering, Renderman, Pencil painting, Fractal, landscape of a Deteriorating The Mesa Verde, Snowy, Single Color, (art by Matt Groening:1.1), interesting background
<lora:TerranTech R1:1> t3rran, full portrait of a (teddy bear:1.2) covered with blue armor, cute teddy eyes, heavy machine, no helmet, very detailed
N/A
Hidden For Public Users
<lora:TerranTech R1:1> t3rran, full portrait of a (teddy bear:1.2) covered with blue armor, cute teddy eyes, heavy machine, no helmet, very detailed

Train Models

Train AI Models On Your Own Pictures

You can use your own pictures to train AI models. Reimagine yourself in new ways with our AI-powered image generator.
Create pictures of yourself around the world, in your dream outfit, as a video game character, or in countless art styles. The possibilities are endless.

Generate AI Images. Simple and Easy

AIEasyPic is the #1 AI image generator. Generate images with simple prompts, swap faces, train models to reimagine yourself, and more.