Introduction
Siveth from the movie Dragonheart: Vengence. This model was trained on a few NSFW pictures plus screenshots from the film itself. Just realized how long this series is after doing up some research, spanning over decades since the first film. Heard it's crap though lol.
This model is now available on both Pony and Illustrious! Read below for prompts and notes.
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 0.6 to 0.8 for best results.
Feral and Anthro (Put "Feral" or "Anthro" trigger words accordingly)
SFW and NSFW
Trigger Words: Siveth_dh
Additional prompts: dragon, white blue scales, wings, white horns, claws, blue eyes, 1girl
Notes
Model is trained on the base Illustrious model.
Generation quality should be about 80 - 85%+ accurate. This means you should generate mostly without much problem with proper prompting, but might still face that occasional error.
If she generates with hair, make sure to include "hair, short hair, long hair" in negatives or increase the weightage of LoRA if you're combining with others.
Pony (V1)
It should be able to generate:
With weightage about 0.6 to 0.8 for best results.
Feral and Anthro (Put "Feral" or "Anthro" trigger words accordingly)
SFW and NSFW
Trigger Words: Siveth_dh
Additional prompts: dragon, white blue scales, wings, white horns, claws, female, 1girl, blue eyes
Notes
Model is trained on the base Pony Diffusion model.
Model may need a lower weightage compared to my other models to generate a better picture quality. I faced some distortions even at 0.8.
Some of my generations were issues with shadows, which i prompted shadows in negatives and bright room in positives. Could be an issue only with Pony Realism, so test it out yourself. Take a look at my generations for examples.
Her eyes could potentially be an issue with the shadows as well. Haven't figured out the best workaround with this yet, so take note of this. Some of my generations were fine, some were just distorted or heavily covered by shadow. (Possibly due to the images that I fed. May retrain this in the near future to see if it helps)
Both Anthro and Feral should work fine, work within the 0.6 to 0.8 range worked very well for me for both forms.
For anthro models, use "hands" and "fingers" in prompts for more proper human anatomy (standard 4 finger 1 thumb) or "claws" if you want a slightly more dragon (typically generates 4 fingers)
For feral models, I tend to include these in negatives: "abs, fingers, belly button, hands, pov, human".
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 This gives me A LOT of buzz, while you can also complete your daily post quest.
Thank you very much!