Hunyuan Video MultiGPU Setup — Multigpu Workflow
Based on hunyuan video wrapper by kijai.
Runtime profile
- Access
- External workflow
- Status
- Listed
- Source
- Civitai
- Updated
- Oct 18, 2026
Source description
Based on hunyuan video wrapper by kijai.
Update 1/1/25
This adds device selection nodes to hunyuan video wrapper.
I have included the workflow.
AND there is a download for the changed files if you want to just manually replace the 2 files in /custom_nodes/Comfyui-HunyuanVideoWrapper/
Or you can download the git from here.
https://github.com/MrReclusive/ComfyUI-HunyuanVWMultiGPU
This has be recoded from the last version to make this all optional, so I could get the pull request approved.
so this IS coming to base hunyuanvideowrapper.
I've modified the nodes to allow selection of device for those with multiple gpu's, this was necessary for me as my system has 2 4090's on a 1x pcie switch, so unloading and loading was slower then generating, with 2 4090's and the 4080 I don't have to unload anything during generation anymore.
What you need
Hardware and download-size estimates are not available yet.
Requirements
Models
5DownloadAndLoadHyVideoTextEncoder
Repository matchedText encoder · Unknown
hunyuan_video_FastVideo_720_fp8_e4m3fn.safetensors
Not resolvedCheckpoint · Unknown
hunyuan_video_vae_bf16.safetensors
PossibleVAE · Unknown
HYNV-Ellie-Lora01.safetensors
Not resolvedLoRA · Unknown
HyVideoVAELoader
Repository matchedVAE · Unknown
Node packs
8HyVideoCudaSelect
Not resolvedNode pack · Unknown
HyVideoDecode
FoundNode pack · Unknown
HyVideoLoraBlockEdit
FoundNode pack · Unknown
HyVideoLoraSelect
FoundNode pack · Unknown
HyVideoModelLoader
FoundNode pack · Unknown
HyVideoSampler
FoundNode pack · Unknown
HyVideoTextEncode
FoundNode pack · Unknown
VHS_VideoCombine
PossibleNode pack · Unknown
AI-generated commentary
AI-generated explanation based on source and configuration details. Suggestions are clearly labeled.
Purpose
Hunyuan Video MultiGPU Setup is a Hunyuan Video workflow for generating video with text encoding, a checkpoint, VAE, and LoRA; its named stages sample, decode, and combine video, and it adds optional device selection for multi-GPU setups.
Inputs and outputs
The listed model files are hunyuan_video_FastVideo_720_fp8_e4m3fn.safetensors, hunyuan_video_vae_bf16.safetensors, and HYNV-Ellie-Lora01.safetensors.
HyVideoDecode and VHS_VideoCombine name the video decoding and combining stages.
Setup
The description offers two ways to add the wrapper changes: replace two files in /custom_nodes/Comfyui-HunyuanVideoWrapper/ or download the ComfyUI-HunyuanVWMultiGPU repository.
Dependencies
Named components include DownloadAndLoadHyVideoTextEncoder, HyVideoCudaSelect, HyVideoDecode, HyVideoLoraBlockEdit, HyVideoLoraSelect, and HyVideoModelLoader.
Other named components are HyVideoSampler, HyVideoTextEncode, HyVideoVAELoader, and VHS_VideoCombine.
Configuration
If you want to choose a device on a multi-GPU setup, use HyVideoCudaSelect; device selection is described as optional.
Suggestion · not verified
Cautions
No license is listed; check the usage terms before reuse.
Suggestion
Does this need to be edited?
Sign in to send an edit request.
Sources
1 source
Sources
1 sourceSource excerpts
1 excerpt
Source excerpts
1 excerptSource context: 641 downloads · Type Workflows · Base model Hunyuan Video
