> ⚠️ The model was trained without any NSFW images. Use it respectfully.
💬 Check out how the prompt examples were set up in the posted images.
💬 Leave your generations in the comments, and tag Lora so I can see how it's looking, it would help a lot.
---
> 👍 Leave a Like — I'm just getting started and it would mean a lot! Have fun! I recommend using a 1024x resolution, share your result and settings so I can improve the LoRA 🔥
For better results, more steps in generation and other BASE models can help, add quality Loras and increase CFG, all images were made with the default settings below
> If you want to try other Steps, leave it in the comments and I'll upload it for you, I have up to 1400
---
⚙️ Generation settings used for preview images
All preview images were generated using:
- Base model: Anima 1.0
- Acceleration LoRA: strength 1.0
- CLIP: anime default
- Steps: 12
- CFG: 1.0
- Sampler: er_sde - beta
---
## 🎴 Hirose & Nakamura | LoRA — Base: ANIMA
📦 Trained with 80 images per character, individually — no NSFW content used in training.
This LoRA covers both characters and works well for solo generations. It can also be used to generate them together — see the prompting tips below for best results.
---
## 👁️ Nakamura
Nakamura has distinctive eyes — reinforce them as much as possible in the prompt for better accuracy. When generating him, place his character tags right after his name in the prompt, and also include them at the beginning of the prompt.
---
## 🎵 Hirose
Responds well to solo generation. Same prompting structure recommended — tags right after the name and at the start of the prompt.
---
## 🤝 Generating both together
When generating both characters in the same scene, use this structure for best results:
- Place each character's specific tags right after their name in the prompt
- Also include both sets of tags at the beginning of the prompt
- Reinforce Nakamura's eyes as much as possible to avoid blending with Hirose's features
---
## 📊 Checkpoints
| Steps | Result |
|-------|--------|
| 800 | Good result |
| ⭐ 1000 | Most balanced — recommended starting point |
| 1200 | Similar to 1000, slightly stronger character imprint |
All checkpoints produce recognizable results. 1000 steps is the sweet spot between accuracy and flexibility.
---