ltxv (13b 0.9.7)

Prompt: "sh1nka1 style A woman stands in a quiet park, the lush greenery around her providing a peaceful backdrop. She wears a white sundress adorned with floral patterns in shades of pink, yellow, and green, the lightweight fabric moving softly with the breeze. A wide-brimmed straw hat rests atop her head, and she wears a pair of large sunglasses that shield her eyes from the afternoon sun. A collection of bracelets jingles on her wrist as she walks along the path, her bare feet gently touching the cool grass. Her long, golden hair falls loosely down her back, and she pauses for a moment to admire the blooming flowers around her, a soft smile playing at the corners of her lips."

Prompt: "sh1nka1 style A man stands at the edge of a quiet, isolated lake nestled deep in a valley, surrounded by dense, towering cliffs. The water is a striking shade of turquoise, and its surface reflects the vibrant green foliage of the trees lining the shore. He wears a soft, rust-colored sweater and a light brown jacket, his hands casually tucked in his pockets. His short, dark hair ruffles in the breeze as he watches the sun dip behind the cliffs, casting the lake in a warm, amber glow. The serenity of the scene envelops him as he takes in the vastness of the untouched wilderness, the only sound the gentle lapping of the water against the shore."

Prompt: "sh1nka1 style A middle-aged woman walks through a bustling farmer’s market, a wicker basket hanging from her arm as she selects fresh fruits and vegetables. She wears a loose, light blue blouse and a wide-brimmed straw hat to shield herself from the sun. Her auburn hair is tied up in a loose bun, and she smiles warmly at the vendor as she picks out a ripe tomato. Her sunglasses rest on her head, and her delicate bracelet catches the sunlight. The market is alive with people, the scent of fresh produce and flowers filling the air as she continues her shopping, her steady pace matching the rhythm of the morning."

Description:

Trainig details:

Trained only on videos.

dataset: 192 videos 864x480x41
steps: 58000
LR: 2e-4
optimizer: adamw
scheduler: contant
rank: 128
batch size: 1
gradient accumulation steps: 1

For training I used the official LTX-Video Trainer repo.

Inference

For inference I used ComfyUI.

Trigger words: sh1nka1 style

Strength: 0.8-1.0

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 called "Tenki no Ko" and "Kimi no Na wa" that 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.

Acknowledgement

Special thanks to Lightricks Team for making this available for the community for free!

Find this LoRA on OpenMuse: https://openmuse.ai/assets/loras/6f4ade0d-e88f-4843-a62c-01ce3f19eb86