---
title: Krea-2-LoRA-kidsdrawing
canonical_url: "https://www.modelscope.ai/models/krea-community/Krea-2-LoRA-kidsdrawing"
md_url: "https://www.modelscope.ai/models/krea-community/Krea-2-LoRA-kidsdrawing.md"
repository: krea-community/Krea-2-LoRA-kidsdrawing
last_updated: 2026-07-01
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - krea/Krea-2-Turbo
base_model_relation: adapter
parameters: 117.3M
tensor_type:
  - F32
library_name:
  - pytorch
  - lora
  - safetensors
frameworks:
  - pytorch
language:
  - en
supports_inference: txt2img
downloads: 132
stars: 0
tags:
  - lora
---

# Krea-2-LoRA-kidsdrawing

> Krea-2-LoRA-kidsdrawing - An open-source model by krea-community on ModelScope. Krea 2 LoRA — kidsdrawing

krea-community/Krea-2-LoRA-kidsdrawing is a 117.3M-parameter text-to-image-synthesis model on ModelScope. licensed under other. derived from krea/Krea-2-Turbo. and supports online inference (txt2img).

- **Repository**: krea-community/Krea-2-LoRA-kidsdrawing
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 117.3M
- **Base model**: krea/Krea-2-Turbo
- **Online inference**: txt2img
- **Tags**: lora
- **Downloads**: 132
- **Stars**: 0
- **Last updated**: 2026-07-01

Source: https://www.modelscope.ai/models/krea-community/Krea-2-LoRA-kidsdrawing

---

# Krea 2 LoRA — kidsdrawing

A LoRA for [Krea 2](https://huggingface.co/krea) — kidsdrawing (trigger: `naive expressive sketch style`).
- **Trigger word:** `naive expressive sketch style`
- **To be used on:** [`krea/Krea-2-Turbo`](https://huggingface.co/krea/Krea-2-Turbo), the few-step distilled checkpoint shown in the previews above.
- **Trained on:** [`krea/Krea-2-Raw`](https://huggingface.co/krea/Krea-2-Raw).
- **Weights:** `kidsdrawing.safetensors`
- **Previews:** rendered on Turbo at 8 steps, guidance 0.0, LoRA weight `1.0`.

## Usage

```python
import torch
from diffusers import Krea2Pipeline

pipe = Krea2Pipeline.from_pretrained("krea/Krea-2-Turbo", torch_dtype=torch.bfloat16).to("cuda")
pipe.transformer.load_lora_adapter("krea/Krea-2-LoRA-kidsdrawing", weight_name="kidsdrawing.safetensors")
pipe.transformer.set_adapters("default", weights=1.0)

prompt = "A deer grazing in the forest, naive expressive sketch style"
image = pipe(prompt, num_inference_steps=8, guidance_scale=0.0).images[0]
image.save("kidsdrawing.png")
```

<Gallery />