Request a LoRA on our Discord and we will train and open-source it for free.

Join our discord to generate videos of the Abandoned Places video LoRA for free.

WAN + HUNYUAN v1.0 :

Trained on 100 images taken from various abandoned places.

Credit to https://civarchive.com/user/CoCatgirl , who posted this training dataset on our Discord!

The trigger word is: 'abandoned places'

Wan 14B T2V Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 6.0

Flow shift = 5.0

Hunyuan Recommended Settings:

LoRA strength = 1.0

Embedded guidance scale = 7.0

Flow shift = 17.0

Check out all our LoRAs on our page: https://app.remade.ai/

Prompt Recommendations:
The model struggles with camera motion, so I would advice describing the camera motion in the prompt. Best to keep the prompt descriptive. Here are some examples that have worked well for me:

Example 1: abandoned places A slow pan through the inside of an abandoned mansion. The camera moves past dusty furniture, cobweb-covered chandeliers, and peeling wallpaper. A curtain flutters slightly from a cracked window, letting in a faint breeze. The sound of distant birds echoes through the empty halls.

Example 2: abandoned places A zoom-in shot starts from a distant view of an overgrown train station, moving closer to show rusting train cars covered in graffiti. Vines creep over the metal, and the camera shifts to reveal a broken railway track disappearing into the dense forest. Leaves flutter in the wind, creating soft movement against the decayed steel.

Example 3: abandoned places A steady zoom-out from the center of an abandoned industrial complex, where a single rusted smokestack stands tall against the cloudy sky. The camera moves back, revealing a network of crumbling buildings and broken glass windows. The sound of distant thunder rumbles as the wind kicks up dust and loose debris.

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