Mirio Togata (Lemillion) | 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. Will it generate NSFW content? Use the adult version of the character. 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 ~266 images. Releasing the 1000 steps checkpoint as it gave the best results — other checkpoints up to 1500 steps available on request.📊 About this modelOn the vanilla ANIMA base, Mirio comes out too generic — he loses his distinctive spiky hairstyle and muscular build, ending up looking like a slim, average anime boy rather than the bulky, larger-than-life hero from My Hero Academia. This LoRA fixes that: it locks in his hairstyle, muscular proportions, and hero costume details much more consistently, making him clearly recognizable across different poses and outfits.ℹ️ Generation tipsOn ANIMA base with 12 steps + acceleration LoRA, the output has a hand-drawn animation feel that works great for Mirio's style — highly recommended as a starting pointUsing more steps or a different ANIMA-based model with quality LoRAs will improve sharpness and detailHigher CFG can help lock in his muscular build and facial features more consistentlyMore steps on the base model are possible but change the aesthetic — personal preference applies hereCheck the prompt examples used in the posted preview images — they show how to structure tags for each outfit📊 CheckpointsStepsResult⭐ 1000 Best balance of style and likeness — recommended, the one being releasedUp to 1500 Available on request — slightly more "locked in" details, but composition/pose gets more repetitive past 1000-1200Want a different checkpoint? Just ask in the comments — I have steps available up to 1500 and can upload them on request.⚙️ Generation settings used for preview imagesAll preview images were generated using:Base model: Anima 1.0Acceleration LoRA: strength 1.0CLIP: anima defaultSteps: 12CFG: 1.0Sampler: er_sde - beta👍 One more thingI'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! 🔥
