MiniMax H3 with all Local LLM System Prompts

This workflow contains system prompts of LLM prompt enhancer for all T2VA, I2VA, L2VA, FL2VA and Ref2VA.

It supports local gguf LLM models. e.g. Gemma 4, Qwen 3.6

No API needed.

Purpose: To make user prompt conform with MiniMax official prompting guide.

• Choose a big MoE LLM model (i.e. something with -A?B) instead of a small non-MoE model.

• Set "cpu_moe": true to speed up LLM with limited vram. (Q8 Gemma 4 26B-A4B model needs only 6GB vram.)

• To set image_min_tokens for Gemma 4, follow n_ubatch > image_max_tokens > image_min_tokens. (e.g. 2240, 2240, 560)

• Qwen 3.6 (e.g. Q6 35B-A3B) can also be used instead of Gemma 4. Just set image_min_tokens to 1024 and n_ctx to a larger value (e.g. 16384).

Custom node used:

ComfyUI_Simple_Qwen3-VL-gguf

ComfyUI_Simple_Qwen3-VL-gguf requires installation of llama-cpp-python wheel and Nvidia CUDA Toolkit. (Comfyui's built-in CUDA might not work.)

e.g.

cmd

cd /d C:\StabilityMatrix\Data\Packages\ComfyUI\venv\Scripts\

python.exe -m pip install ???.whl

ComfyUI-SolAttn_triton

System prompts modified from:

H3_LLM_Instructions

rzgar

Thanks for their work. Cheers.