With the Anima version, you have greater freedom to write prompts in natural language. It is highly recommended to use it together with the Anima Highres and Anima Turbo LoRAs for noticeably better image quality. I'll be working on providing a higher-fidelity version later. As for LoRA weight, please decide based on your own needs — if you're aiming for an illustrative look, a lower LoRA weight generally yields better results. Hope you enjoy using it!
using the two-character lora model trained by Noobai, there is a high possibility of bad pictures in two-person interaction, please try more.
cgf:5-5.5
step:20-25
weight: 0.6-0.8
Description
Rumi & Sakie's Anima model version. Anima is still in the exploratory stage, and many aspects are not yet fully refined — please bear with us. For prompts, you can use natural language or write with regular tags. If anything is unclear, you can refer to the example images for guidance. Please note that this version suffers from overfitting and may produce blurry images. I will work on releasing an additional version later to address these issues.