This is a Krea 2 LoRA trained on 150 high-quality splash art illustrations (16:9 landscape).
🎨 Trigger Word:
Add lorst at the end of your prompt to activate the style.
⚙️ Recommended Settings:
- Base Model: Krea 2
- Sampler: Euler
- Scheduler: Simple
- Steps: 10 - 12
- CFG: 1.0
- Recommended Weight: 0.5 - 0.8 (adjust to your preference)
🖼️ What it does best:
This LoRA captures the highly detailed, cinematic, and dramatic lighting of modern game splash arts. It excels at epic compositions, vibrant color contrast (especially warm and cool tones), and rich textures for characters and environments. It is perfect for generating fantasy warriors, magical scenes, and dynamic wide-angle shots.
⚠️ Notes:
This is a pure style LoRA. It does NOT lock you into specific characters. You can use it with any character prompt, and it will apply the splash art style to them. For best results, keep your prompts in natural language (full sentences). Avoid writing "league of legends splash art" in your prompt, as the trigger word lorst takes care of that.
Negative Prompt: (Optional for Krea 2)
blurry, lowres, bad anatomy, bad hands, text, watermark, ui, jpeg artifacts.
Description
v1.0 Initial release. Trained on 150 high-quality League of Legends splash art images (16:9). Uses the lorst trigger word. Recommended for Krea 2.
FAQ
Comments (5)
fyi: lorst as title and triggerword, but filename is "lost" instead, accidental misnaming? Very minor thing, but fixing it might help people find the lora in a long lora-list later.
Thank you so much for catching that! You're absolutely right—it was an accidental typo. The trigger word is lorst but the file was named lost. I'll rename the file in a future update to make it easier to find. Really appreciate your help!
Why are there two of these? Am I missing something? https://civitai.red/models/2924911/lorst-krea2-splash-art?modelVersionId=3309669
Thank you for pointing this out! I'm still getting familiar with the platform's rules. Because I couldn't find my first upload initially, I thought it had failed and accidentally published it twice. They are exactly the same model. I will delete the earlier duplicate soon and learn the platform better. Really appreciate your heads-up!
@lianglennie545 no worries its a great model thats why I noticed lol