Introduction

Just another amateur remix of the Anima model.

With this model, you can create many fascinating artworks, just like an amateur.

Required Components

1. Text Encoder: https://huggingface.co/circlestone-labs/Anima/resolve/main/split_files/text_encoders/qwen_3_06b_base.safetensors?download=true

1. VAE: https://huggingface.co/circlestone-labs/Anima/resolve/main/split_files/vae/qwen_image_vae.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

1. Unless explicitly specified, version 1.0 is likely to produce characters in red eyes, especially under dark environment

2. 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