---
title: wan22_5b_i2v_crush_it_lora
canonical_url: "https://www.modelscope.cn/models/ostris/wan22_5b_i2v_crush_it_lora"
md_url: "https://www.modelscope.cn/models/ostris/wan22_5b_i2v_crush_it_lora.md"
repository: ostris/wan22_5b_i2v_crush_it_lora
last_updated: 2025-07-31
license: apache-2.0
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - Wan-AI/Wan2.2-TI2V-5B
base_model_relation: adapter
parameters: 80.6M
tensor_type:
  - BF16
library_name:
  - lora
  - diffusers
  - safetensors
  - pytorch
frameworks:
  - pytorch
downloads: 255
stars: 1
tags:
  - text-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# wan22_5b_i2v_crush_it_lora

> wan22_5b_i2v_crush_it_lora - ostris 在 ModelScope 开源的模型。Wan 2.2 5B I2V Crush It LoRA

ostris/wan22_5b_i2v_crush_it_lora 是 ModelScope 魔搭社区上的 80.6M 参数text-to-image-synthesis模型，采用 apache-2.0 许可，基于 Wan-AI/Wan2.2-TI2V-5B 构建。

- **Repository**: ostris/wan22_5b_i2v_crush_it_lora
- **License**: apache-2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 80.6M
- **Base model**: Wan-AI/Wan2.2-TI2V-5B
- **Tags**: text-to-image, lora, diffusers, template:diffusion-lora
- **Downloads**: 255
- **Stars**: 1
- **Last updated**: 2025-07-31

Source: https://www.modelscope.cn/models/ostris/wan22_5b_i2v_crush_it_lora

---

# Wan 2.2 5B I2V Crush It LoRA

<Gallery />

## Model description 

This is an Image to Video LoRA trained while filming a tutorial with [AI Toolkit](https:&#x2F;&#x2F;github.com&#x2F;ostris&#x2F;ai-toolkit). That tutorial video can be found here: [How to Train a Wan 2.2 5B Image to Video LoRA With AI Toolkit](https:&#x2F;&#x2F;youtu.be&#x2F;9ATaQdin1sA)
 
<video controls>
  <source src="https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/bJA4EweDbmtxv7BIfJAL8.mp4" type="video/mp4">
</video>

<video controls>
  <source src="https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/qkOftFq48uMLOsJA7HzGr.mp4" type="video/mp4">
</video>

<video controls>
  <source src="https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/Co_-7f2FAGfChJHpirlmw.mp4" type="video/mp4">
</video>

<video controls>
  <source src="https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/A33LduVwrKxfO2QR-QtrV.mp4" type="video/mp4">
</video>

<video controls>
  <source src="https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/AiYizPm2cj9VCYhFgI0Qi.mp4" type="video/mp4">
</video>

## Trigger words

You should use `crush it` to trigger the image generation.


## Download model


[Download](/ostris/wan22_5b_i2v_crush_it_lora/tree/main) them in the Files & versions tab.