This is my current workflow for the HunyuanVideo model in ComfyUI
-Hunyuanvideo T2V
-Hunyuanvideo T2V Batch
-Hunyuanvideo V2V
-Hunyuanvideo V2V Batch
Thanks to Kijai for his nodes
Description
FAQ
Comments (4)
How are you getting the sharpness and realism on some of your examples?
I noticed it often does an unrealistic artwork style rather than realistic without me prompting for it. Are negative prompts possible as i haven't really used comfy much?
Any tips on consistent realism and higher quality would be great. Even running at 1280x720 i often find it lacks sharpness expected and i think its mainly down to prompts with this. I'm not sure but the steps doesn't seem to make much difference?
Also got sage attention to work and didn't notice much improvement on a 3090?
My brother in Christ, why not share the actual workflow json instead of images like what?
There are only .png files in the latest download.
Hi, will these workflow be updated to support Hunyuan node changes? These don't seem to work with the latest changes.
Looks like we don't have an active mirror for this file right now.
CivArchive is a community-maintained index — we catalog mirrors that volunteers upload to HuggingFace, torrents, and other public hosts. Looks like no one has uploaded a copy of this file yet.
Some files do get recovered over time through contributions. If you're looking for this one, feel free to ask in Discord, or help preserve it if you have a copy.