Download
1 variant available
fp16 SafeTensor
yt_yorime_zimage_260821.safetensors
Half precision, best balance • 44 MB
Verified: 4 days ago
650 1 2 3 4 5 6 7 8 90 1 2 3 4 5 6 7 8 9
00 1 2 3 4 5 6 7 8 9
(4)
Aug 21, 2026
This LoRA was specifically designed to be used in combination with other LoRAs. Since base models like Z-Image have high LoRA tolerance/durability, feel free to layer it with your favorite style, character, or pose LoRAs!
Show more
License:
Apache 2.0This LoRA is designed to add natural and realistic cross-eyed expressions to your characters. Trained primarily on photorealistic images, it works surprisingly well across various scenarios, styles, and facial expressions.
Usage & Settings
Trigger Word: yt_yorime
Additional Prompts: cross-eyed, looking at own nose (helps reinforce the focal point) Recommended Weight: 0.7 – 1.0 (adjust to fit your base model)
Tips & Compatibility
Flexible Expressions: It supports a wide range of facial expressions, including smiles, surprised looks, tongue-out faces, and intense focus! Creative Ideas: Try pairing it with fun prompts—like a sci-fi glitch effect, extreme concentration during delicate work (like soldering), or a tiny bug sitting right on the character's nose.


