Introduction

Jean the Ender Dragon from Minecraft.

This model is now available on both Pony and Illustrious! Read below for prompts and notes.

Pony V1 is trained on feral model dataset, while Pony V2 is trained on her anthro model dataset. Either LoRA should be capable to generate both Anthro and Feral.

Illustrious LoRA combines both dataset together into one model.

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.

• Anthro and Feral (Put "Feral" and "Anthro" trigger words accordingly)

• SFW and NSFW

Prompts

Trigger Words: jean_mc

Additional prompts: dragon, black scales, wings, horns, tail, claws, purple eyes, white underbelly, 1girl

optional prompts: white underbelly, black underbelly, white horns, black horns, white wings, black wings (You can mix and match, but include either to improve generation consistency)

Notes

• Model is trained on the base Illustrious Model.

• Quality Generation is about 85% - 90%+ accurate. This means you should be able to generate without much issues with proper prompting. Use the optional prompts to get more consistent generations.
  

• I've included black/white underbelly, horns and wings prompt. Include these to generate more consistency with your generations or you might randomly generate either color every time.
  

• Feral seem to have some issues while I was generating with various pose as it still seem to generate anthro for some reason. Do include 'Anthro, breasts, navel' in negatives and increase weightage if needed, but it might cause some weird generations. This model seem to favor anthro more still somewhat.
  

Anthro (V2)

It should be able to generate:

• With weightage about 0.8 to 1.

• Anthro and Feral (Put "Feral" and "Anthro" trigger words accordingly)

• SFW and NSFW

Prompts

Trigger Words: jean_mc

Additional prompts: dragon, black scales, wings, horns, tail, hands, female, 1girl, purple eyes

optional prompts: white underbelly, black underbelly

Notes

• Model is trained on the base Pony Diffusion model.
  

• Overall model generates much better than the feral with more consistency than I expected. Partially also it has a larger training set.
  

• This model should generate with a white underbelly most of the time unless otherwise prompted.
  

• 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".

Feral (V1)

It should be able to generate:

• With weightage about 0.8 to 1.

• Anthro and Feral (Put "Feral" and "Anthro" trigger words accordingly)

• SFW and NSFW

Prompts

Trigger Words: jean_mc

Additional prompts: dragon, black scales, wings, horns, tail, claws, female, 1girl, purple eyes

optional prompts: white underbelly, black underbelly

Notes

• Model is trained on the base Pony Diffusion model.
  

• Trained this model using feral only models, but it should be capable of producing both anthro and feral models.
  

• Seems like the model is generating okay, but sometimes with inconsistent colors. You can specify either 'white underbelly' or 'black underbelly' to achieve better consistency across your generations.
  

• Tested with about 80% accuracy, aiming to increase this in V2 to 90% at least.
  

• 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:

1. Liking my posts, collecting my images or collecting my models all generate buzz for me.

2. Generate more pictures of my models. I get a base commission from anyone who generates using my model, even without the tip.

3. Leave a like on my model. This helps me with the algorithm in reaching more people

4. Leave a review. I take all feedback very seriously, good or bad.

5. Consider using the 'add post' under gallery... if you are posting pictures of just my LoRA. The images will also pictures will still appear on your profile but this will give me A LOT of buzz, while you can also complete your daily post quest.
   
   

   Thank you very much!