ovi054/LTX-2-19b-ghibli-style-LoRA

LTX-2-19b-ghibli_style-LoRA

This is a fine-tuned version of ltx-2-19b-dev.safetensors trained on custom data.

Sample Outputs

Prompt A young woman with short, wind-swept hair stands on a lush green hilltop, clutching a straw hat. Below her, a sea of grass ripples in rhythmic waves like the ocean. In the background, massive, towering Laputa-style clouds drift slowly across a brilliant blue sky. The animation is fluid, focusing on the flutter of her dress and the shimmering light of the afternoon sun. Cinematic, painterly, and serene.

Usage

This model is designed to be used with the LTX-2 (Lightricks Audio-Video) pipeline.

🔌 Using Trained LoRAs in ComfyUI

In order to use the trained LoRA in ComfyUI, follow these steps:

1. Copy your trained LoRA checkpoint (.safetensors file) to the models/loras folder in your ComfyUI installation.
2. In your ComfyUI workflow:
   • Add the "Load LoRA" node to choose your LoRA file
   • Connect it to the "Load Checkpoint" node to apply the LoRA to the base model

You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the official LTX-2 repository.

Trigger Words

• Studio Ghibli hand-drawn cel animation style

Example Prompts

Example prompts used during validation:

• A young woman with short, wind-swept hair stands on a lush green hilltop, clutching a straw hat. Below her, a sea of grass ripples in rhythmic waves like the ocean. In the background, massive, towering Laputa-style clouds drift slowly across a brilliant blue sky. The animation is fluid, focusing on the flutter of her dress and the shimmering light of the afternoon sun. Cinematic, painterly, and serene.

This model inherits the license of the base model (ltx-2-19b-dev.safetensors).

Acknowledgments

• Base model: Lightricks
• Trainer: LTX-2