Another ST workflow, but hopefully not as big as some of the others I've seen. On my 3060, images take 15s to finish, and all 28 takes about 7 minutes. Updates are mostly to fix node problems. If yours works, there's no need to update. Works best on images with black backgrounds.There are more instructions in the workflow, but the most important thing to remember is to set the batch size to 28 to get all the emotes.Nodes aligned with NodeAligner: <a target="_blank" rel="ugc" href="https://github.com/Tenney95/ComfyUI-NodeAligner">https://github.com/Tenney95/ComfyUI-NodeAligner</a>This was made with a version of Comfy with an older version of Python (from 6/27/25). Newer versions have some crap about WAS Suite and whatever OpenCV is that prevents Comfy from launching properly.

Sillytavern Expressions Workflow

This is a minor update that uses Anima instead of an XL model. About as fast, with better prompt following... Lora: <a target="_blank" rel="ugc" href="https://civitai.com/models/2619830/turbo-for-anima-less-steps">https://civitai.com/models/2619830/turbo-for-anima-less-steps</a>

Files with SHA256: 75e481ebe2e5d9d5105460b1f3f4c17d48b85abee5efa67f1ef89016cd2d3734