Which Model To Use?

v1: Rainwing | v2: Grandeur & Magnificent

• Rainwing (V1) can be used to generate generic rainwings, and specific characters such as Glory, Kinkajou and Jambu

• Grandeur & Magnificent (V2) can be used to generate both Grandeur and Magnificent. I recommend combining this LoRA with the base LoRA to reduce distortions. Use either their tags to trigger the respective character (See notes on how I do this or check out my pictures.)

---

Grandeur & Magnificent (V2)

Grandeur & Magnificent from the book series Wings of Fire. Two former Rainwing queens before the throne was eventually passed on to the current Queen Glory.

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 0.8 to 1 for best results.

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

• SFW and NSFW

Prompts

Trigger Words for Grandeur: Grandeur_wof, purple scales, female, 1girl, blue eyes

Trigger Words for Magnificent: Magnificent_wof, magenta scales, female, 1girl, green eyes

Optional prompts: Rainwing, dragon, ear ruffs, head fins, scales, horns, claws, wings, tail

Notes

• Model is trained on the base Pony Diffusion model.

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

• Prompting either Grandeur or Magnificent should easily give their color style. Grandeur may be a bit more random considering the training images. Also, generating in certain styles (like Pony Realism) might make them look a lot younger considering Grandeur is supposed to be quite elderly.

• In terms of color accuracy, it should be about 80 - 90%. In terms of generating the actual character face shapes, probably only about 60 - 70%. Grandeur looks way too young in most of my generations even in other styles. Could be because of my V1 LoRA that affects this but have yet to test separately.

• 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".

---

Rainwing (V1)

Rainwings from the book series Wings of Fire. A mix of SFW and NSFW Images were used to train this model. This model can be used to generate Glory and Kinkajou since this model is trained on a lot of their pictures, but it may be fully color accurate.

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

• Glory, Kinkajou, Jambu

• Rainwing scales of all colors!

Prompts

Trigger Words: Rainwing

Additional prompts: dragon, ear ruffs, head fins, scales, horn, claws, wings, tail

Prompt for Glory: Glory, green scales, female, 1girl

Prompt for Kinkajou: Kinkajou, pink scales, female, 1girl

Prompt for Jambu: Jambu, pink scales, male, 1boy

Notes

• Model is trained on the base Pony Diffusion model.

• Glory is about 80-90% accurate. After initial testing, adding the words "orange feet" and "orange wings" may help get Glory to a more 'accurate' color.

• Kinkajou is about 70-80% accurate. Still sometimes generate her full pink. Adding the word 'orange underbelly' may help but not 100% so pray to RNGesus if you choose to generate her.

• Jambu should be 90-100% since he's just all pink which is easy for the AI.

• 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!

描述:

First version with Glory, Kinkajou and Jambu

训练词语: Rainwing, dragon, ear ruffs, head fins, scales, horn, claws, wings, tail,Glory, green scales, female,Kinkajou, pink scales, female,Jambu, pink scales, male