---
title: krea2_turbo_style_reference
canonical_url: "https://www.modelscope.cn/models/ostris/krea2_turbo_style_reference"
md_url: "https://www.modelscope.cn/models/ostris/krea2_turbo_style_reference.md"
repository: ostris/krea2_turbo_style_reference
last_updated: 2026-07-09
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - krea/Krea-2-Turbo
base_model_relation: adapter
parameters: 228.5M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - diffusers
  - safetensors
frameworks:
  - pytorch
supports_inference: txt2img
downloads: 285
stars: 2
tags:
  - text-to-image
  - lora
  - diffusers
  - "template:diffusion-lora"
---

# krea2_turbo_style_reference

> krea2_turbo_style_reference - ostris 在 ModelScope 开源的模型。Krea 2 Style Reference LoRA

ostris/krea2_turbo_style_reference 是 ModelScope 魔搭社区上的 228.5M 参数text-to-image-synthesis模型，采用 other 许可，基于 krea/Krea-2-Turbo 构建，并支持在线推理（txt2img）。

- **Repository**: ostris/krea2_turbo_style_reference
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 228.5M
- **Base model**: krea/Krea-2-Turbo
- **Online inference**: txt2img
- **Tags**: text-to-image, lora, diffusers, template:diffusion-lora
- **Downloads**: 285
- **Stars**: 2
- **Last updated**: 2026-07-09

Source: https://www.modelscope.cn/models/ostris/krea2_turbo_style_reference

---

# Krea 2 Style Reference LoRA

<Gallery />

## Model description 

This LoRA will allow you to inference on the Krea2 Turbo model in the style of a reference image. It was trained with [AI Toolkit](https://github.com/ostris/ai-toolkit) using the experimental Krea2 reference image trainer with the turbo training adapter. It was trained on thousands of hand curated style pairs I have been building over the years. It was trained to handle 1-2 reference images.

For inference in Comfy UI you will need this custom node. [ComfyUI-Krea2-Ostris-Edit](https://github.com/ostris/ComfyUI-Krea2-Ostris-Edit) Use the template in that repo with this lora for the effect. No trigger word is needed just image and prompt. 


For diffusers, there is a communiuty pipeline here [ostris/Krea2OstrisEdit](https://huggingface.co/ostris/Krea2OstrisEdit). You can run it like below:

```python
import torch
from diffusers import DiffusionPipeline
from PIL import Image

pipe = DiffusionPipeline.from_pretrained(
    "krea/Krea-2-Turbo",
    custom_pipeline="ostris/Krea2OstrisEdit",
    torch_dtype=torch.bfloat16,
)
pipe.enable_model_cpu_offload()  # or pipe.to("cuda") with ~40+ GB of VRAM

# An AI-Toolkit Krea 2 LoRA, e.g. the style reference LoRA
pipe.load_lora_weights(
    "ostris/krea2_turbo_style_reference", weight_name="krea2_style_reference.safetensors"
)

image = pipe(
    "a white yeti with horns reading a book",
    image=Image.open("style_reference.png"),  # one reference image or a list of them
).images[0]
image.save("output.png")
```

![ref_009](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;LUWIOTqblW9crkzBRce3S.jpeg)


![ref_006](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;rSsEXZuvsQJLARGkcG2pJ.jpeg)


![ref_001](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;7q8KuTmLdr_OucvFi84QB.jpeg)


![ref_002](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;x5NsP9fr6V-3CvjvG2ISI.jpeg)


![ref_003](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;BRMgfUvrGQgxuj1Ms6dJw.jpeg)


![ref_004](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;yHpyB4d3xhuw_gh4JjUL_.jpeg)


![ref_005](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;VPy0ubelM9GPA6XaR6No_.jpeg)


![ref_007](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;Cekmn7X8lqAHt08OhPBIQ.jpeg)


![ref_010](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;Mj3RX3F-mIOBfjYXa_fy0.jpeg)


![ref_012](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;QANQnlbgOTlmyVxTiOpOH.jpeg)


![ComfyUI_temp_bgxgv_00080_](https:&#x2F;&#x2F;cdn-uploads.huggingface.co&#x2F;production&#x2F;uploads&#x2F;643cb43e6eeb746f5ad81c26&#x2F;57lTVnFsvEhYfCNrFNfJF.jpeg)


![ref_008](https://cdn-uploads.huggingface.co/production/uploads/643cb43e6eeb746f5ad81c26/G5xcb4YsCGYdURdMkDSzk.jpeg)

## Download model


[Download](/ostris/krea2_turbo_style_reference/tree/main) them in the Files & versions tab.
