---
tags:
- text-to-image
- lora
- diffusers
- template:diffusion-lora
widget:
- output:
    url: images/1-kitchen.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/7-fox.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/6-wolf.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/5-bus.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/4-beach.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/3-street.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
- output:
    url: images/2-floor.png
  text: KABAPASTE The girl is squeezed from a tube like paste.
base_model: Lightricks/LTX-2.3
instance_prompt: KABAPASTE
license: other
license_name: ltx-2-community-license-agreement
license_link: https://github.com/Lightricks/LTX-2/blob/main/LICENSE
---
# 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 &quot;guides&quot;. They are in native Comfy, so it won&#39;t add load.

The workflow is in the videos metadata or inside &#x60;kabapaste-workflow.json&#x60; at my [Huggingface page](https:&#x2F;&#x2F;huggingface.co&#x2F;kabachuha&#x2F;ltx23-paste).

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.

Trigger phrase is:

&#x60;KABAPASTE The girl is squeezed from a tube like paste.&#x60;

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

## Trigger words

You should use `KABAPASTE` to trigger the image generation.


## Download model


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