|
|
--- |
|
|
base_model: |
|
|
- Wan-AI/Wan2.2-T2V-A14B |
|
|
tags: |
|
|
- text-to-video |
|
|
- lora |
|
|
widget: |
|
|
- text: >- |
|
|
"[APPEARANCE] Nfj1nx wears a deep-cut, form-fitting black evening gown with |
|
|
a high slit, allowing ease of movement and a striking silhouette. Her long |
|
|
midnight-blue hair flows over one shoulder in polished waves. [ENVIRONMENT] |
|
|
A dimly lit, smoky salon draped in shadows and flickering amber light. |
|
|
Velvet armchairs, dark wooden décor, and heavy curtains define the |
|
|
atmosphere. Smoke curls through the air, catching beams of light from |
|
|
scattered wall lamps. Faint silhouettes shift in the background, hidden |
|
|
behind haze and shadow. [CUT 1] Action: Nfj1nx stands still in the middle of |
|
|
the salon, her pistol lowered at her side. Camera: Rapid arc shot circling |
|
|
from her front-left to back-right at waist level. [CUT 2] Action: She raises |
|
|
the pistol with a smooth, deliberate motion, arm fully extended and steady. |
|
|
Camera: Fast dolly-in from floor level toward the gun, then tilting up to |
|
|
catch her eyes." |
|
|
output: |
|
|
url: assets/test_00043.mp4 |
|
|
--- |
|
|
|
|
|
# wan 2.2 (14b T2V) |
|
|
|
|
|
<Gallery /> |
|
|
|
|
|
## Inference |
|
|
For inference I used ComfyUI. |
|
|
|
|
|
**The strength of the LoRA can differ from prompt to prompt. As best practice, I suggest always checking the high model inference and adjusting the high noise LoRA strength or the steps accordingly. Mostly it is optimal when the character features are just beggining to appear in the high model inference, but aren't prominent yet.** |
|
|
|
|
|
**Trigger words**: Nfj1nx, blue hair |
|
|
|
|
|
**Strength**: 0.6-1.2 |
|
|
|
|
|
## Trainig details |
|
|
Trained only on videos. |
|
|
|
|
|
### HIGH noise LoRA |
|
|
- dataset: 30 videos 480x270 25,33,65,81 frame videos |
|
|
- steps: 2130 |
|
|
- LR: 5e-5 |
|
|
- optimizer: AdamW Optimi |
|
|
- rank: 32 |
|
|
- batch size: 1 |
|
|
- gradient accumulation steps: 1 |
|
|
- min_t = 0.875 |
|
|
- max_t = 1 |
|
|
|
|
|
### LOW noise LoRA |
|
|
- dataset: 42 videos 640x360 25,33,65 frame videos |
|
|
- steps: 2730 |
|
|
- LR: 5e-5 |
|
|
- optimizer: AdamW Optimi |
|
|
- rank: 32 |
|
|
- batch size: 1 |
|
|
- gradient accumulation steps: 1 |
|
|
- min_t = 0 |
|
|
- max_t = 0.875 |
|
|
|
|
|
For training I used the diffusion-pipe repo. |
|
|
|
|
|
***Important Notes:*** |
|
|
This LoRA is created as part of a fan project for research purposes only and is not intended for commercial use. It is based on the movies, which are protected by copyright. Users utilize the model at their own risk. Users are obligated to comply with copyright laws and applicable regulations. The model has been developed for non-commercial purposes, and it is not my intention to infringe on any copyright. I assume no responsibility for any damages or legal consequences arising from the use of the model. |
