Anima base int8 / mxfp8

Versions

• int8: recommended. Fast, accurate, compatible with almost any GPU.

• mxfp8: added for comparison. In theory (and according to nVidia PR) should be more accurate than int8, but in practice I was not able to spot any definitive advantages. A bit slower than int8, but still faster than original bf16. Compatible only with RTX 50xx series (Blackwell).

Performance on my setup

• original bf16 (baseline): 2.20 it/s +0%

• int8: 3.23 it/s +46%

• int8 + torch compile (comfy core): 3.59 it/s +63%

• int8 + turbo lora, cfg=1: 6.50 it/s +295%

• int8 + turbo lora, cfg=1 + torch compile (comfy core): 7.55 it/s +343%

• mxfp8: 2.58 it/s +17%

This is high quality int8 quantized version of base Anima v1.0 model. It retains ~90% of original model quality, but uses about 50% less VRAM and also runs faster on almost any nVidia GPU (AMD not tested). Nice trade-off, especially for low-end GPUs.

Can be used as a drop-in replacement for original Anima model in latest ComfyUI, no custom nodes required. If you have troubles running the model make sure that you updated both ComfyUI itself and its dependencies (e.g.pip install -U -r requirements.txt on manual linux install).

Converted to int8 / mxfp8 using convert_to_quant script.