For more Workflows and updates, Join my Discord:
https://discord.gg/ZVWVhT43GW
You can deploy MiniMax on RunPod with my template: https://get.runpod.io/minimax-template
Workflow:
Minimax supports up to 18 inputs at once, wiring and bypassing nodes is a pain.
So I created this custom node that allows you to add/remove references for Minimax ReferenceToVideo, you only have to wire it once.
Some more neat features:
- Automatic prompt writing via OpenRouter/Local LLMs, returns structured Minimax prompts based on your description (opt in)
- Save prompt/reference packs and reuse them.
Custom node:
Nodes:
https://github.com/Hearmeman24/ComfyUI-MiniMaxRefPack
This workflow also come preinstalled on my Runpod template.
Description
This was the most requested change.
I added some bug fixes and support for local LLM providers.
FAQ
Comments (5)
How did they all get flyaway hair? Didn't see it in the prompt.
This one works perfectly with local host. choose LLM (I used Ollama and Qwen3 abliterated), check for the local ip host through powershell command, make sure you're not connected. no issues so far. Better than your previous one. Great work.
Just a noob question, I guess. How do I add the a scheduler node with this workflow? I wanted to choose beta with Seed2 or Euler.
Thanks, it's on the right next to the references node
@HearmemanAI thanks for the tips. Just FYI: You still need to activate the internet to even access the LLM. It stills logs in to local host but requires the access of the internet or the node does not work. Any ideas?
how do you get the lora trigger words to appear in the auto prompt text? I include them in my prompt, but the auto prompt never uses them.
Also, is there a way to adjust the size of the prompt entry window? I can' t see a way to do it and with it only being an inch or so tall, it is cumbersome to use.