metadata
tags:
- lora
- diffusers
- template:diffusion-lora
- text-to-video
- t2v
widget:
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/IS4AQXKB9vRg32SdfQonM.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/pHGLSK3WUJ0rimzcHqpX7.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/gizLfc-23-TiI7gBsHQE_.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/g7sS9I55LxV5WqKd9Ik-o.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/S5Q0UiY3x2AXXgYdGaykc.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/3XPlDkzMZaXnA-ultk4US.mp4
text: '-'
- output:
url: >-
https://cdn-uploads.huggingface.co/production/uploads/653cd3049107029eb004f968/7uq7CBsrPPH9EfaOS7h0P.mp4
text: '-'
base_model:
- Wan-AI/Wan2.2-T2V-A14B
instance_prompt: null
1980s fantasy movies Wan2.2 T2V 14B
My first Wan lora, so expect sub optimal settings. It uses the same dataset as https://huggingface.co/neph1/1980s_Fantasy_Movies_Hunyuan_Video_Lora. Some things work incredibly well, but in some cases Hunyuan wins.
Low noise model is trained for 30 epochs.
High noise model is trained for 20 epochs.
No logic behind it, I just got tired of waiting.
Prompt example: "a woman warrior clad in steel and chain armor. she walks through a mysterious swamp. she looks wary. mist, smoke rising from the ground, she's holding a staff. dead trees, the scene invokes adventure and mystery, the camera follows the woman ahead"
Download model
Download them in the Files & versions tab.