POV Driving (Hunyuan Video LoRA)

Join our Discord community where you can generate videos, share ideas and request LoRAs, to push the bounds of the technology!

HUNYUAN v1.0 :

Trained on Hunyuan Video fp8 with 29 POV driving videos, all 5 seconds long.

The trigger word is: p0v_dr1v1n6

For the best results, we also want to describe details of the driving along with the trigger word. See examples below for prompts that worked well.

Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 7.0

Flow shift = 17.0

Prompt Recommendations:

Best to keep the prompt relatively simple, here are some examples that have worked well for me:

Example 1: 'p0v_dr1v1n6, video shows a person driving a car through Minecraft. The driver is holding the steering wheel with both hands. The blocky road stretches ahead, made entirely of pixelated cobblestone. Villagers stand on the side, nodding weirdly. The driver is looking straight ahead. The car has a digital dashboard and a touchscreen display'

Example 2: p0v_dr1v1n6, video shows a person driving a car through a burning hellscape. The driver is holding the steering wheel with both hands. Rivers of lava flow on both sides of the cracked road, and firestorms rage in the distance. The driver is looking straight ahead. The car has a digital dashboard and a touchscreen display flickering with demonic symbols.'

Example 3: 'p0v_dr1v1n6, video shows a person driving a car on a rainbow road floating in space. The driver is holding the steering wheel with both hands. The road has no guardrails, and planets drift lazily in the background. The driver is looking straight ahead. The car has a digital dashboard and a touchscreen display'

Let me know if there are any questions, I'll be happy to help!