home models images videos posts articles bounties challenges events updates shop

Hunyuan Video i2v + v2v + Low Vram with upscale | Modular Image Gen i2i + CNET + Upscale

Name: Hunyuan Video i2v + v2v + Low Vram with upscale | Modular Image Gen i2i + CNET + Upscale
Rating: 5 (78 reviews)
Author: Daemonrat

3.1k

Updated: Feb 4, 2025

tool

workflow hunyuan low-vram

Download (3.09 MB)

Verified: 6 months ago

Other

Details

Type	Workflows
Stats	1,919 0
Reviews	Very Positive (56)
Published	Feb 1, 2025
Base Model	Hunyuan Video
Hash	AutoV2 CE15391DFF

1 File

About this version

The blue side is Hunyuan video gen, the pink side is an image gen workflow that supports multiple models. On the pink side you can expect to use 1.5, XL and Flux. Maybe SD 2.x/3.x but I haven't tested that yet. There's CNET for Flux and CNET for 1.5/XL.

Blue side probably only works with Hunyuan for now, I haven't added support for other video gen models. Ultimate Upscale for Hunyuan video is untested, lmk how it goes if you do try it out.

i2v/v2v seems to work fine. i2v is kind of a hack by looping the image for "x" number of frames. i2v will need higher denoise to make the video animated. If the denoise is too low, it will mostly be a still frame video.

I was going to keep NF4 support for image gen, but it's too complicated for new users to set up the bitsandbytes nodes, so it has been removed.

Side note: I'm working on an LLM chat workflow now so that I no longer need to leave comfy for my AI needs.

default creator card background decoration

Daemonrat

Tencent Hunyuan is licensed under the Tencent Hunyuan Community License Agreement, Copyright © 2024 Tencent. All Rights Reserved. The trademark rights of “Tencent Hunyuan” are owned by Tencent or its affiliate.

Hotfix 2/4/25 - Culled unused group nodes. This should reduce the required dependencies when installing.

READ ABOUT THIS VERSION |------------>

Feedback is appreciated, but if you're rude or uninformed, you will simply be ignored or blocked.

GGUF:

https://huggingface.co/city96/HunyuanVideo-gguf/tree/main

Fast Video Lora:

https://huggingface.co/Kijai/HunyuanVideo_comfy/tree/main

Pretty much everything else can be found on Civitai by sorting the model category by Hunyuan Video.

Some Comfy extensions were used, just click install missing and it should install them. If you run into any errors run update all, uninstall broken nodes and try installing them again, the comfyui manager is not perfect.

There's an issue with comfy where sometimes after installing new nodes, they'll show as missing in the workflow. If this happens, drag the .json file into comfy again and it should load them this time.