---
title: krea-2-pastel-chinese-dreamscape-lora
canonical_url: "https://www.modelscope.cn/models/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora"
md_url: "https://www.modelscope.cn/models/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora.md"
repository: ilkerzgi/krea-2-pastel-chinese-dreamscape-lora
last_updated: 2026-07-03
license: other
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - krea/Krea-2-Turbo
base_model_relation: adapter
parameters: 234.6M
tensor_type:
  - BF16
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
supports_inference: txt2img
downloads: 28
stars: 3
tags:
  - lora
  - text-to-image
  - krea
  - krea-2
  - fal-ai
  - "template:diffusion-lora"
  - illustration
---

# krea-2-pastel-chinese-dreamscape-lora

> krea-2-pastel-chinese-dreamscape-lora - ilkerzgi 在 ModelScope 开源的模型。Pastel Chinese Dreamscape

ilkerzgi/krea-2-pastel-chinese-dreamscape-lora 是 ModelScope 魔搭社区上的 234.6M 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**: ilkerzgi/krea-2-pastel-chinese-dreamscape-lora
- **License**: other
- **Tasks**: text-to-image-synthesis
- **Parameters**: 234.6M
- **Base model**: krea/Krea-2-Turbo
- **Online inference**: txt2img
- **Tags**: lora, text-to-image, krea, krea-2, fal-ai, template:diffusion-lora, illustration
- **Downloads**: 28
- **Stars**: 3
- **Last updated**: 2026-07-03

Source: https://www.modelscope.cn/models/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora

---

<picture>
  <source media="(prefers-color-scheme: dark)" srcset="https://huggingface.co/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora/resolve/main/fal-dark.png">
  <img src="https://huggingface.co/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora/resolve/main/fal-light.png" alt="fal" height="18">
</picture>

# Pastel Chinese Dreamscape

**fal · Krea 2 Style LoRA series.** One of 1600+ style LoRAs trained on [fal](https://fal.ai).

A **Krea 2** style LoRA. Add the trigger **`pastel chinese dreamscape style`** to the end of your prompt.

[![Run on fal.ai](https://img.shields.io/badge/Run_on-fal.ai-FF6B35?style=for-the-badge)](https://fal.ai/models/fal-ai/krea-2/turbo/lora) [![Train on fal.ai](https://img.shields.io/badge/Train_on-fal.ai-FF6B35?style=for-the-badge)](https://fal.ai/models/fal-ai/krea-2-trainer) [![Krea 2](https://img.shields.io/badge/base-Krea_2_Turbo-7C5CFF?style=for-the-badge)](https://huggingface.co/krea/Krea-2-Turbo)

<Gallery />

## Quick start

| Parameter | Value |
|-----------|-------|
| Trigger | `pastel chinese dreamscape style` |
| Recommended LoRA scale | `1.0` to `1.25` |
| Base model | `krea/Krea-2-Turbo` |
| Trained on | [fal-ai/krea-2-trainer](https://fal.ai/models/fal-ai/krea-2-trainer) |

## Inference on fal

### Python
```python
import fal_client

result = fal_client.subscribe(
    "fal-ai/krea-2/turbo/lora",
    arguments={
        "prompt": "a lighthouse on a rocky cliff. pastel chinese dreamscape style",
        "loras": [{"path": "https://huggingface.co/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora/resolve/main/pastel-chinese-dreamscape.safetensors", "scale": 1.0}],
        "image_size": {"width": 1024, "height": 1280},
    },
)
print(result["images"][0]["url"])
```

### JavaScript
```js
import { fal } from "@fal-ai/client";

const { data } = await fal.subscribe("fal-ai/krea-2/turbo/lora", {
  input: {
    prompt: "a lighthouse on a rocky cliff. pastel chinese dreamscape style",
    loras: [{ path: "https://huggingface.co/ilkerzgi/krea-2-pastel-chinese-dreamscape-lora/resolve/main/pastel-chinese-dreamscape.safetensors", scale: 1.0 }],
    image_size: { width: 1024, height: 1280 },
  },
});
console.log(data.images[0].url);
```

## Train your own on fal

Every LoRA in this series is trained on [`fal-ai/krea-2-trainer`](https://fal.ai/models/fal-ai/krea-2-trainer) (100 steps, learning rate 3.5e-4). Train your own style from 4 to 10 reference images:

```python
import fal_client

result = fal_client.subscribe(
    "fal-ai/krea-2-trainer",
    arguments={
        "images_data_url": "https://.../your-dataset.zip",
        "trigger_phrase": "pastel chinese dreamscape style",
        "steps": 100,
        "learning_rate": 0.00035,
    },
)
print(result)
```

## License

Krea 2 Community License. See the [license](https://huggingface.co/krea/Krea-2-LoRA-impressionist/blob/main/LICENSE.pdf).

## ComfyUI

A ComfyUI-compatible copy of the weights is included in this repo: **`pastel-chinese-dreamscape-comfy.safetensors`**. It is the
exact same LoRA with the key prefix remapped (`base_model.model.` to `diffusion_model.`) so
ComfyUI loads it directly. Download that file into `ComfyUI/models/loras/` and use it like
any other LoRA. The original `pastel-chinese-dreamscape.safetensors` is for [fal](https://fal.ai) / diffusers.