---
tags:
- image-to-video
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: video_examples/1-kitchen.mp4
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: video_examples/2-floor.mp4
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: video_examples/3-street.mp4
  text: >-
    KABAPASTE The girl is squeezed from a tube like paste. The video is silent
    with the sound of rain and squeezing sounds. After the girl forms, her
    umbrella opens up.
- output:
    url: video_examples/5-bus.mp4
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: video_examples/6-wolf.mp4
  text: KABAPASTE The wolf is squeezed from a tube like paste.
- output:
    url: video_examples/7-fox.mp4
  text: KABAPASTE The girl is squeezed from a tube like paste.
base_model: Lightricks/LTX-2.3
instance_prompt: KABAPASTE The girl is squeezed from a tube like paste.
license: other
license_name: ltx-2-community-license-agreement
license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
language:
- en
pipeline_tag: image-to-video
---
# LTX-2.3 Paste Squeeze

<Gallery />

## Model description 

Squeeze your characters from a tube like liquid paste!

**BIG NOTE:** This is a **Last** frame to video LoRA and you need to use frame "guides". They are in native Comfy, so it won't add load.

The workflow is in the videos metadata or inside `kabapaste-workflow.json`; at my [Huggingface page](https://huggingface.co/kabachuha/ltx23-paste/tree/main).

As you may notice, the videos are at 50 FPS. Otherwise, the workflow is fully default, but with 30 steps and distill lora strength at 0.6 for reportedly higher quality. It uses KJ nodes for image resize and VHS for metadata saving.

For training details, see my other recent 2.3 LoRAs on Huggingface.

## Trigger words

Trigger phrase is:

`KABAPASTE The girl is squeezed from a tube like paste.`

## Download model

[Download](/kabachuha/ltx23-paste/tree/main) it in the Files & versions tab.