REanimaTE - [BDD] 3D/CG Edition
This is an alternative fine-tune from BDD that shifts the focus toward a sharp, high-cohesion 3D/CG aesthetic while retaining the core flexibility and stability from the base Anima model. By dialing back real-world images in the datasets, this version delivers cleaner lines, enhanced crispness, and a distinctly polished rendering style.
What’s New:
Enhanced 3D Depth: Sharper, more defined cinematic and CG rendering.
Retained Flexibility: Preserves the strong prompt adherence and structural cohesion of base Anima.
Usage & Recommendations:
Dataset Focus: Trained with a strong emphasis on high-quality NSFW aesthetics.
Core Prompting: Optimized and tested for 1girl subjects. While standard anime variety is fully supported, composition variety may be slightly tighter due to the focused training set.
Description
Updated - more anime coherence, less realistic
FAQ
Comments (7)
Awesome model. Thank you!
What's the name of your character splitting node? I can't seem to find it
Oh, that's a custom node I made for myself to make generating sample images easier. It isn't posted anywhere - you can just use a regular text multiline node instead.
@CallMeMaybe 谢谢
Best Anima model I've found so far, by far.
Love this model, but I really liked the soft 3D style of 1.0, are you going to deviate further from it or try to get back to it? It made the model stand out to me.
the soft 3d style is actually the intent of this model, the problem with 1.0 was that I felt it lost a meaningful amount of the consistency with the anima dataset and characters and compositions were less consistent. I've been working at enhancing my dataset with more characters and variety to try to bring back that soft 3d style - but in the meantime I made v2.0 because I felt it still did a good job of adding a consistent semi-realistic 2.5D style but much more consistent with the anima characters and compositions compared with v1.0
tldr; yes, but it's hard work expanding my dataset =) - this is a model finetune, not a lora merge