If you’d like to show some love, feel free to react w/ emoji, post, rate, follow, or simply drop some feedback, I'd appreciate it. 🫡🫰 Feel free to also report any issues.
The Anima LoRA uses a completely redone dataset. Mostly newer images with only some pre-2025. A pain removing panels, komas, text bubbles, and more again. Also, took 6 LoRA adjustments to get right 😭.
Anima Base v1.0
Images trained and generated on Anima - base-v1.0. My generation details: CFG: 5, Steps: 20-30 and Sampler: DPMPP 2M Simple, and SeedVR2. If you're using the site's generator, lower steps to 15-20, you may also switch away from base to avoid fees (try WAI-ANIMA/MiaoMiao) . Feel free to experiment!
Trigger Word: @chxrrygxg
Illustrious trigger word: chxrrygxg
Eye problems/smudging happens way less often in Anima. It handles off styles better. If you can't use ADetailer, try Anima.
Description
Mainly focuses on images between 2025-2026.
FAQ
Comments (10)
Wow these look amazing!!!
Glad you like it. Also, based username and pfp 🔥
@Ty_Lee ❤️❤️❤️
Great stuff Ty Lee. Works wonders!
How about Tarakanovich aka Gockroach, if you don't mind? Last loras on CIvit are based on NAI :(
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.