import torch
from diffusers import DiffusionPipeline
from diffusers.utils import load_image, export_to_video
# switch to "mps" for apple devices
pipe = DiffusionPipeline.from_pretrained("Lightricks/LTX-2", dtype=torch.bfloat16, device_map="cuda")
pipe.load_lora_weights("ovi054/LTX-2-19b-Squish-LoRA")
prompt = "A man with short gray hair plays a red electric guitar."
input_image = load_image("https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/diffusers/guitar-man.png")
image = pipe(image=input_image, prompt=prompt).frames[0]
export_to_video(output, "output.mp4")LTX-2-19b-Squish-LoRA
This is a fine-tuned version of ltx-2-19b-dev.safetensors trained on custom data.
| Example 1 | Example 2 |
|---|---|
| Example 3 | Example 4 |
|---|---|
| Example 5 | Example 6 |
|---|---|
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:
- Copy your trained LoRA checkpoint (
.safetensorsfile) to themodels/lorasfolder in your ComfyUI installation. - 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 Word
squish it
This model inherits the license of the base model (ltx-2-19b-dev.safetensors).
Acknowledgments
- Base model: Lightricks
- Trainer: LTX-2
- Downloads last month
- 221
Model tree for ovi054/LTX-2-19b-Squish-LoRA
Base model
Lightricks/LTX-2