Introducing: MINIMAX H3 | EZ REF WF
NOTICE: I posted this right before Darksidewalker posted the Dasiwa Minimax H3 WF, i suggest you use that one instead, its far more advanced than this one.
https://civarchive.com/models/2831978/dasiwa-minimax-h3-workflows-or-t2va-or-fl2va-or-ref2va
I will not be updating or fixing any issues going forward as this Workflow was meant as a quick "upgrade" from the base workflow before any advanced ones dropped, and since one has now there's no point using this one.
a custom workflow for Minimax's H3 video model. Its not too different to the base one Comfy provides, just has some little tweaks that i like to use, including Sage Attention/Easy Cache Patch.
Please be aware this is for the minimax_h3_ref2va_pruned_int8_convrot.safetensors model.
This workflow is my personal workflow that I use for all of my Minimax H3 stuff, it may not be to everyone's taste but it works well for me and I'm sure others may find it useful.
Generated a 5 second clip with 0.6MP at 16:9 in 6:32 on an RTX 3060 12GB/32GB Sys RAM using this WF. base workflow was more than double that time.
Works on 12GB VRAM + 32 GB System RAM. not tested on anything below.
INCLUDES:
3 Ref Images | 1 Ref Audio
Sage Attention Patch (For Lower VRAM Use)
Easy Cache
Bob INT8 Loader (Faster INT8 Loading)
Kofi: https://ko-fi.com/mrweaz
Nodes Needed:
https://github.com/kijai/ComfyUI-KJNodes
https://github.com/BobJohnson24/ComfyUI-INT8-Fast
https://github.com/Comfy-Org/Nvidia_RTX_Nodes_ComfyUI
Disclaimer: I hold no liability for any images produced, including their legality, ethical implications, or potential misuse. By using this model, you agree that all responsibility for generated content rests solely with you. Use responsibly and within legal boundaries.
Description
Added RTX Upscaler
Replaced SageAtt and EasyCache.
FAQ
Comments (14)
The Dasiwa link is dead.
надеямся и ждем)
Works fine for me 🤷
a bit of a noob here, but it says it is missing MiniMaxH3MemoryEfficientSageAttentionPatch?
Oh no probs, you need to Update KJNodes manually, you need the latest build. If you have done that and still.persists either update ComfyUI or you don't have sage-attention installed.
Nice work! Fun to explore h3 with. Is there a way to add first/last frame on top of this? Too often it just ignores prompting for <image 1> to be the first frame.
Yeah this workflow is just for reference, if you want FFLF, change the model to the FL one, replace the MinimaxH3 reference node to the FL one and delete the IMG3/Audio nodes and plug everything back into the FL node. It's a quick fix, but yeah this WF was just for reference mode
@mrweaz Gotcha, thanks. Guess there's no way to combine both nodes yet.
@bugmaker86 there is, but you'll need to use switches and bypassers, I was planning on expanding this WF to make use of both, but a more advanced one dropped right after so I'm not updating this one anymore as it's not as advanced 😂
Id recommend you try the Dasiwa one, it's much better.
@mrweaz I'll check it out. 😉
6 minutes for 10sec at 12fps 320x600p on laptop rtx-A2000- 8GB vram , but loaded the 64GB ddr5 ram to 58GB/64GB! The results are definitely worth waiting for, compared to both LTX and WAN.
throw a RIFE interpolator in there and you are golden
Unable to get the "RTX" nodes working. import failed. Everything is up to date and of course i have an RTX GPU
try git cloning directly into your custom nodes folder, sometimes comfy can fail to import, always good practice to clone manually