Hirose & Nakamura | LoRA — Base: ANIMA

🙏 Before anything else: this LoRA took a lot of work — picking the images, building the dataset and tags, training, and testing the checkpoints. If you have a moment, drop a Like and especially post your results in the comments (with the prompt/settings you used) — it helps me a lot to know what to improve in the next versions. 🔥

⚠️ 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 the LoRA so I can see how it's looking, it would help a lot.

📦 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.

📊 About this model

👁️ 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.

ℹ️ Generation tips

• On ANIMA base with 12 steps + acceleration LoRA, the output keeps a clean anime feel that works well for both characters — recommended as a starting point

• Using more steps or a different ANIMA-based model with quality LoRAs will improve sharpness and detail

• Higher CFG can help lock in their facial features more consistently

• Check the prompt examples used in the posted preview images — they show how to structure tags for each character

🤝 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

StepsResult 800 Good result

⭐ 1000Most balanced — recommended starting point, the one being released

1200 Similar to 1000, slightly stronger character imprint

All checkpoints produce recognizable results. 1000 steps is the sweet spot between accuracy and flexibility.

Want a different checkpoint? Just ask in the comments — I have steps available up to 1400 and can upload them on request.

⚙️ Generation settings used for preview images

All preview images were generated using:

• Base model: Anima 1.0

• Acceleration LoRA: strength 1.0

• CLIP: anima default

• Steps: 12

• CFG: 1.0

• Sampler: er_sde - beta

👍 One more thing

I'm just getting started with this — if you have a moment, drop a Like and share your generations with the settings you used. It really helps me improve the next versions. Have fun! 🔥