base_model:
- Wan-AI/Wan2.1-T2V-14B
tags:
- text-to-video
- lora
widget:
- text: >-
"walgro style. A couple sits on a cozy balcony, overlooking a quiet,
moonlit cityscape. The woman leans into the man's chest, her hand resting
gently on his. She wears a flowing silk robe in a soft lavender hue, the
fabric catching the light from the candles surrounding them. Her long,
auburn hair cascades down her back, and her delicate fingers intertwine
with his. The man, dressed in a loose button-up shirt, his sleeves rolled
up, has his arm wrapped around her waist. He gently brushes his lips
against her forehead, his eyes closed in contentment. The soft hum of the
city below contrasts with the peaceful intimacy they share, and they both
smile quietly as the night deepens."
output:
url: assets/singles_00001.mp4
wan 2.2 (14b T2V)
- Prompt
- "[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."
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.