First attempt at a HunyuanVideo LoRA:
Arnold Schwarzenegger - Trigger is "ohwx person" - include "ohwx person" in your prompt to call up the Arnold likeness.
Note: If you have an issue where it seems like the LoRA isn't doing anything at all, try changing the "Load_Device" on the "HunyuanVideo Model Loader" node to "OffLoad Device" (instead of "main_device"). That should resolve it.
Strength recommendations: 1 to 1.25 - boost it up a bit if the model doesn't incorporate "ohwx person" enough. The likeness is definitely there at a strength of 1, but raising the strength to 1.15 (for example) will increase the likelihood that the model will focus on "ohwx person" (Arnold) and not something else in the prompt.
Description
FAQ
Comments (11)
Amazing 👀👀👀👀👀
LFG!!!
Was this trained on video or images. Could you share your training settings if at all possible please
Woah very nice, any tutorial or tips for training?
was hard to do? can we train on windows?
How do you use this? I don't see a Lora node in the workflows? Help?
new era just started
We finally have our first Video LORA! Lets gooo :D
So awesome. We need a skin realism Lora :p
not working with my workflow
Your advice about "load_device" saved me. Thank you!
Details
Files
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.