Simple conversion of Crody's <a target="_blank" rel="ugc" href="https://civarchive.com/models/2604424/nova-anime-am">Nova Anime AM v4.0</a> model. All credit to them.Still my favorite Anima base. works incredibily well without the need of quality tags while still providing a good basis for style tags and LoRAs.Why int8 when the model is already so small? Speed.Int8-convrot provides around a 50% speed-up in generation times on my RTX 3070 (39s vs 56s on BF16) with virtually no decrease in quality.tool used for conversion: <a target="_blank" rel="ugc" href="https://github.com/Starnodes2024/comfyui-starnodes-modelconverter">https://github.com/Starnodes2024/comfyui-starnodes-modelconverter</a>my recommended settings for fast generation:ER SDE - simple - cfg 1 - 16 steps - <a target="_blank" rel="ugc" href="https://civarchive.com/models/2560840/anima-turbo-lora">Turbo LoRA </a>@ 0.5 strength

Nova Anime AM - [Int8-convrot]

Simple conversion via Starnodes Model Converter in ComfyUI.

Files with SHA256: a0d50098a282c1c4fd72352400094c4c38684c33ee399db0cf4d10379ad2a87e