Introduction
Just another amateur remix of the Anima model.
With this model, you can create many fascinating artworks, just like an amateur.
Required Components
Text Encoder: https://huggingface.co/circlestone-labs/Anima/resolve/main/split_files/text_encoders/qwen_3_06b_base.safetensors?download=true
Alternative VAE: QwenimageVAE_liquid1087
Recommended Settings
Sampler: Euler A / ER SDE / dpmpp_2m_sde_gpu
Scheduler: Simple / Beta
Steps: 30-50 steps
CFG: 4-5
If you're using TURBO for ANIMA, you might start off with 12 steps with CFG 1.0.
Known Issues / Limitations
Unless explicitly specified, version 1.0 is likely to produce characters in red eyes, especially under dark environment
Stacking too many style LoRAs on top of this model might lead to over-saturation
License
https://huggingface.co/circlestone-labs/Anima/blob/main/LICENSE.md
Description
Less chance to produce red eyes under dark environment
Better lighting/contrast