Introduction
Shyvana from League of Legends. This model is specifically for her new dragon form that was released together with her rework back in March 2026.
This model was trained on a number mix of SFW and NSFW pictures, with screenshots from the game as well.
Also, it's a small training pool so errors might be expected as I'm learning how to train with the new AI Toolkit too. Still learning, and making sure it maintains the same quality of LoRAs I make. (PS. If you face any issues or have any suggestions, just leave a comment on the LoRA or DM me)
Using This LoRA and want to support me? Use the 'add post' in the gallery below - This gives me a lot of blue buzz to train more LoRAs!
Illustrious (V1)
It should be able to generate:
With weightage about 0.8 to 1.2.
Feral and Anthro (Put "Feral" and "Anthro" trigger words accordingly)
SFW and NSFW
Prompts
Trigger Words: shyvanadragon_lol
Additional Prompts: dragon, red scales, orange mane, gray underbelly, gold spikes, gold neck armor, red horns, black horn tips, wings, grey wings, claws, tail, yellow eyes, 1girl
Notes
Model is trained on the base Illustrious Model.
Generation quality should be about 85 - 90% Accurate. This means you shouldn't have much issues with proper prompting.
Since this model is trained on only feral/quadruped form, anthro form may face some slight issues since AI like to fill in the gaps especially the hair. So if you're generating her as an anthro, take note of this.
Also her tail isn't trained properly since there was insufficient training data so you'll get different generations of it if you don't prompt something you want and leave it as it is.
Could also due to small dataset training, but her eyes may have some issues generating properly at times. Using a LoRA for eyes helps this a little bit (see my pics for examples)
Want to support me without Tipping? Here's how:
Liking my posts, collecting my images or collecting my models all generate buzz for me.
Generate more pictures of my models. I get a base commission from anyone who generates using my model, even without the tip.
Leave a like on my model. This helps me with the algorithm in reaching more people.
Leave a review. I take all feedback very seriously, good or bad.
Consider using the 'add post' under gallery... if you are posting pictures of just my LoRA. This gives me A LOT of buzz, while you can also complete your daily post quest.
Thank you very much!