metadata
tags:
- ltx-video
- image-to-video
pinned: true
language:
- en
license: other
pipeline_tag: text-to-video
library_name: diffusers
ltxv_2b_lora_soft_draw_v1
This is a fine-tuned version of LTXV_2B_0.9.6_DEV trained on custom data.
Model Details
- Base Model:
LTXV_2B_0.9.6_DEV - Training Type: LoRA fine-tuning
- Training Steps: 3000
- Learning Rate: 0.0002
- Batch Size: 2
Sample Outputs
Usage
This model is designed to be used with the LTXV (Lightricks Text-to-Video) pipeline.
🔌 Using Trained LoRAs in ComfyUI
In order to use the trained lora in comfy:
- Copy your comfyui trained LoRA weights (
comfyui..safetensorsfile) to themodels/lorasfolder in your ComfyUI installation. - In your ComfyUI workflow:
- Add the "LTXV LoRA Selector" node to choose your LoRA file
- Connect it to the "LTXV LoRA Loader" node to apply the LoRA to your generation
You can find reference Text-to-Video (T2V) and Image-to-Video (I2V) workflows in the official LTXV ComfyUI repository.
Example Prompts
Example prompts used during validation:
a snowy village square during a gentle snowfall, with twinkling holiday lights, warmly dressed people strolling past market stalls, and a large decorated tree at the centera deep underwater scene with shafts of light breaking through the surface, illuminating coral reefs and schools of colorful fish swimming gracefully through the blue depths.a dramatic cliffside overlooking a stormy sea, where crashing waves slam against the rocks below, and dark clouds churn above, hinting at an approaching tempest.a peaceful rural farm at sunrise, with golden light spilling across open fields, a red barn in the distance, and a few grazing animals starting their day.
This model inherits the license of the base model (LTXV_2B_0.9.6_DEV).
Acknowledgments
- Base model by Lightricks
- Training infrastructure: LTX-Video-Trainer



