Instructions to use oumoumad/LTX-2-19b-LoRA-TEAR with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Diffusers
How to use oumoumad/LTX-2-19b-LoRA-TEAR with Diffusers:
pip install -U diffusers transformers accelerate
import torch from diffusers import DiffusionPipeline # switch to "mps" for apple devices pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", dtype=torch.bfloat16, device_map="cuda") pipe.load_lora_weights("oumoumad/LTX-2-19b-LoRA-TEAR") prompt = "TEAR 3d object stretch and bend to get torn slowly" image = pipe(prompt).images[0] - Notebooks
- Google Colab
- Kaggle
- Local Apps
- Draw Things
TEAR

- Prompt
- TEAR 3d object stretch and bend to get torn slowly
- Negative Prompt
- repeat, fade
Model description
This is an LTX-2 LoRA trained on videos of an objects getting torn in 3d allowing you to create videos like this using a start image of any subject :
Trigger word
start with "TEAR" and optionally end with "getting torn" or "gets torn"
Download model
Download them in the Files & versions tab.
Examples
- Downloads last month
- 436
Model tree for oumoumad/LTX-2-19b-LoRA-TEAR
Base model
Lightricks/LTX-2