This is a highly optimized, mixed-precision (MXFP8) quantized version of the Anima Base 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.Performance &amp; Stats vs Original Anima V10:<ul><li>VRAM Usage: ~2.2 GB (Reduced from ~4.0 GB)</li><li>File Size: 2.15 GB (Reduced from ~4.0 GB)</li><li>Generation Speed: ~2.3 it/s (Increased from ~1.9 it/s)</li><li>Precision: Mixed-precision (<code>mxfp8</code>, <code>int8</code>, <code>float8</code>)</li></ul>

Files with SHA256: 1101d5091ab7853ad9581c07ea68efd08c70d2b007448b15a67c4e5874c36f65