ghost
Sign In

Typhon (Arknights)

39
381
383
2
Verified:
SafeTensor
Type
LoRA
Stats
381
383
Reviews
Published
Aug 6, 2023
Base Model
SD 1.5
Training
Steps: 1,240
Epochs: 8
Usage Tips
Clip Skip: 2
Trigger Words
typhon
dragon horns, dragon tail, very long hair, hairband, purple hair, red eyes
Hash
AutoV2
E07404A9AB
default creator card background decoration
allureAI's Avatar
allureAI

Typhon (Arknights)

Please feel free to rate the model or share your creations with it. I'd be thrilled to see your works. If you find it useful, consider showing your appreciation by buying me a coffee.

  • Weight: between 0.8 to 1.0

  • Trigger Word: typhon

  • Negative Prompts: (wings, dragon_wings:1.2)

Additional Prompts:

  • With Attire: dragon horns, dragon tail, very long hair, hairband, purple hair, red eyes, black shirt, black shorts, garter straps, grey coat, off shoulder, open coat, (asymmetrical legwear, single thighhigh:1.2), thigh strap

  • Character Only: dragon horns, dragon tail, very long hair, hairband, purple hair, red eyes

Suggested Hires.fix configuration:

  • Upscaler (For Anime Models): R-ESRGAN 4x+ Anime6B

  • Upscaler (For PhotoReal Models): R-ESRGAN 4x+

  • Hires steps: between 10 to 20

  • Denoising strength: between 0.15 to 0.35

Each time I invest a significant amount of time testing my trained LoRA on my favorite base models, I discover something unique. For this iteration, the character features a horns, tail, single thighhigh with thigh strap and multiple belts. While these attributes made the results somewhat unpredictable, it added a creative touch. The results were particularly intriguing when rendered in Perfect World V4 & V5. Notably, Perfect World V5 enhanced the character, making her appear even more juicy and thicc voluptuous and pronounced lol.

Your comments or suggestions are not only welcome but can significantly improve the quality of my models. They also motivate me to create more LoRA models. Feel free to connect with me on my Discord channel.

V2 was trained on the AnyLoRA base model with a dataset comprised of 32 images.

The compatibility of this LoRA model has been tested and work well with the following base models:

Anime models:

  • DreamShaper V8

  • MeinaMix V11

  • Perfect World V5

  • Perfect World V4

Photorealistic models:

  • Realistic Vision V5.1

  • Henmix_Real V4

All demonstration images showcased are randomly selected, not handpicked for optimal results.