Which Model To Use?

v1: Mudwing | v2: Queen Moorhen

• Mudwing (V1) can be used to generate generic mudwings, and specific characters such as Clay

• Queen Moorhen (V2) can be used to generate Queen Moorhen. I recommend combining this LoRA with the base LoRA to reduce distortions. (See notes on how I do this or check out my pictures)

Queen Moorhen (V2)

Queen Moorhen from the book series Wings of Fire. Made this one especially after her latest illustration came out.

A mix of SFW and NSFW pictures were used for this model, with some help from the graphic novel as well too.

I would recommend combining both this LoRA and V1 at the same time. See notes on what I did.

It should be able to generate:

• With weightage about 0.6 to 0.8 for best results.

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

• SFW and NSFW

Prompts

Trigger Words: Moorhen_wof

Additional prompts: gem embedded face, gemstones, green eyes, female, 1girl

Optional prompts: Mudwing, brown scales, dragon, horns, claws, wings, tail,

Notes

• Model is trained on the base Pony Diffusion model.
  

• Recommended to use the base version as well since the version is trained on a lot of mudwing pictures. Generating just V2 alone might cause more errors and distortions. My settings for V2 is set at 0.7 - 0.8, and V1 at 0.5 - 0.6 so it picks up more on Moorhen but still can generate the mudwing anatomy.
  

• The gemstones on her face may be a little random due to the training. I did not train this on any prompt so take note of it. Mostly, blue or green gemstones seem to appear on her face which is close to what is shown in her latest depiction.
  

• I had to reduce my generations for V1 and V2 to 0.5 and 0.7 respectively to get more consistent generation. Take note of this as compared to my other LORAs (Snowfall, Blister, Coral, etc) where I used 0.6 for V1 and 0.8 for V2. Adjust accordingly if you see inconsistent or distorted images.

• 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".

Mudwing (V1)

Mudwings from the book series Wings of Fire. A mix of SFW and NSFW Images were used to train this model.

It should be able to generate:

• With weightage about 0.8 to 1 for best results.

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

• SFW and NSFW

• Male and Female models

• Clay, of course!

Prompts

Trigger words: Mudwing

Additional Prompt: brown scales, dragon, horns, claws, wings, tail

Prompts for Clay: Clay_wof, male, 1boy

Notes

• Model is trained on the base Pony Diffusion model.

• Not much issues from testing. Should reliably generate Clay quite well by using the prompts.
  

• 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!