Turns expressions into a transparent-animated AVIF files - works with SillyTavern. This is an extension of my SillyTavern Anima Workflow. I designed this workflow for maximum speed, after all, 26 expressions is a lot of videos to do and redo.
(This workflow is designed for the more knowledgeable ComfyUI user)

Update Notes (0.5):

Removed Export Frames and Save Animated WEBP nodes (Figured this was bloat and you can do it yourself). Removed Preview Video (wasn't working). Cleaned up nodes, did some tweaks for speed enhancements (batch interpolation processing and remove duplicate frames). Edited and reviewed minimax LLM instructions, now polished. Added a speedup and interpolation to the transition between last frame and first frame; it's not perfect but better than what it was.

Requirements:

• SillyTavern Character Expression Generation Workflow

• Soft requirements (In other words requires tweaking workflow to avoid using these):
  - KJ's FP8 MiniMax H3 (Ada+Blackwell generation only)
  - Minimax-h3-Turbo
  (Use the int 8 version of Minimax and it's turbo lora if Ampere)
  - Better Human Motion Minimax (SFW)
  - Slop Bounce (SFW & NSFW)
  - 2D Anime Style (NSFW)
  - Mystic XXX (NSFW)
  - Faster! Harder! (NSFW)

• DavidAU's Qwen38TTurboFableFusion735 + mmproj-BF16 (Or your own LLM and mmproj) - Place in ~/.../ComfyUI/models/LLM/GGUF

• Foge's Save Animated AVIF Node - (Was on old ComfyUI-Manager repo, now you need to clone it): [ Download ] (Plus my script [included])

#!/bin/bash
cd ComfyUI/custom_nodes
git clone https://github.com/foge1024/ComfyUI-AVIF-Animation

• Viggle's Sigma node: [ Download ] & Viggle's turbo 6 step (best version is int 8 convrot) [ Download ]

#!/bin/bash
cd ComfyUI/custom_nodes
wget https://huggingface.co/Viggle/Qwen-Image-2.1-viggle-turbo/raw/main/comfyui/viggle_turbo.py

Operation:

My Anima Workflow: Mode 8 -> 'Run'
Use generated image with white background as well as the prompt and plug it in to this workflow.
(Generated prompt can also be found in image's .json 'negative prompt' section)
(Example Prompt:)

Lewdness: Low
Expression: Joy
Character Tags: Elf, blonde, tunic
Character Actions: laughing, smiling

(Feel free to tweak the input as you like, but leave lewdness and Expression alone, it's used in the logic of this workflow)

Technical Note:

This uses ComfyUI-LLM-text-processor node set. Means you need llama.cpp installed inside of your ComfyUI environment.

#!bin/bash
cd ~/.../ComfyUI/custom_nodes
source ./venv/bin/activate
python -m pip install llama-cpp-python
# Run ComfyUI
python main.py --listen --port 8188 --enable-manager

Linux Users (Like myself): LLM node might point to the wrong binary, paste:
llama_cli.py & llama_binary.py
from:
.../ComfyUI/custom_nodes/ComfyUI-LLM-text-processor
Into your favorite AI bot and ask it to fix it to work with your distro of linux. Personally, I had to SED a few lines to get mine to work.

Two, alternatively, you can opt for another node set to replace the 'LLM' node, such as the QwenVL Nodes, which come self-contained with auto downloaders (But may require you to figure out your own system instructions and Setup).

Second Note: Interpolation is done by tensorRT, CUDA acceleration. AMD users, you can swap these out with other ones if you need to. This workflow is yours to tweak to your specs.