This is my daily driver MiniMax H3 Workflow designed for my rig.
This is NOT a basic workflow.
This is NOT meant as a low VRAM workflow.
This is NOT meant to be a workflow centered around specific base models or LoRAs and is not meant to be a prompt and click generator. I experiment a lot and this workflow is meant for this purpose.
There are tips and instructions in the workflow, so I won't elaborate much on instructions for use. I don't know if this is the right way, but it's my way. :)
This Workflow includes:
LoraManager Lora Loader and TriggerWord Toggle, because if you aren't using LoRA Manager, WTF are you doing?
H3 Multishot Sampler (one node)
MultiGPU Model Loaders
Sage Attention Options:
MiniMax Mem Eff Sage Attention
Patch Sage Attention KJ
Comfy Kitchen Attention
Veda Sparse Attention
MiniMax H3 Chunk FeedForward and MiniMax H3 Low VRAM Attention
Impact Wildcard Processor for wildcard {|} prompts
DaSiWa Enhanced Video Combine because it is really good.
Model Preview Override
Start Image input, 6 reference image inputs and 3 Audio inputs
I don't have an Upscaler included because I use a separate workflow for upcaling and interpolation. https://civarchive.com/models/2972841/video-upscale-and-interpolation
Primary groups are free floating to arrange wherever you want without breaking the workflow and no annoying spline webs.
There are links to basic base, text encoder and VAE models as well as Accelerator LoRAs in the workflow. I am leaving it up to you to find the non-standard models if you want to use them and ComfyUi makes that pretty easy now.
Please make sure you look at the instructions for the models you want to use for best practices for steps, scheduler/sampler and cfg settings.
if you want instruction for any of the nodes I use, please look to the creator's documentation. I do have suggested settings for different model profiles in the workflow note nodes. Example images have metadata and workflows embedded.
This workflow is a work in progress and I will update it with any major changes as they happen.
Feel free to message me and ask questions and I will do my best to help you when I am able.
Description
FAQ
Comments (4)
Bro, i have 2 GPU - 5070ti 16gb and 3060 12gb
Gpu-device all set and pinned memory off.
And after text encoder loaded to the 3060, the Minimax ref2V prepare before the sampler throws "cannot find file" errors.
Could not find module 'libcudart.so' (or one of its dependencies). Try using the full path with constructor syntax.
It is mandatory to have 2 identical graphics cards for MultiGPU, or what i did wrong?
No. Not identical, I use a 4090 and an A4000 Ada. I am not sure that is GPU related. I would use Claude or another good LLM and copy the error into the chat and see what it says. Also, Make sure your comfyui is updated.
Everytime I try to run this one, I get the same error about VRAM cleanup, even after I tried turning it off.
# ComfyUI Error Report ## Error Details - Node ID: 2215:2214 - Node Type: VRAMCleanup - Exception Type: TypeError - Exception Message: TypeError: VRAMCleanup.empty_cache() got an unexpected keyword argument 'input'
Make sure your ComfyUI and nodes are updated. Use a good LLM, like Claude, to Troubleshoot your ComfyUI. This is not a workflow issue.