This is a highly optimized, mixed-precision (MXFP8) quantized version of the Anima Turbo V1.0 model. It was created to provide a much lighter and faster generation experience without noticeably sacrificing visual fidelity.

If you are running on a GPU with limited VRAM, or if you want to free up memory to run heavier ComfyUI workflows (like multiple ControlNets, upscale pipelines, or LoRAs), this checkpoint is for you.