---
title: KleinBase4B-aerialview-garden-photorealistic-dea05d
canonical_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d"
md_url: "https://www.modelscope.cn/models/diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d.md"
repository: diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d
chinese_name: "俯瞰、园林、写实"
last_updated: 2026-10-03
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
base_model:
  - black-forest-labs/FLUX.2-klein-base-4B
base_model_relation: adapter
parameters: 14.7M
tensor_type:
  - BF16
library_name:
  - pytorch
  - lora
  - safetensors
supports_inference: img2img
downloads: 3
stars: 0
tags:
  - LoRA
  - text-to-image
---

# KleinBase4B-aerialview-garden-photorealistic-dea05d

> KleinBase4B-aerialview-garden-photorealistic-dea05d - diffsynth-i2L-gallery 在 ModelScope 开源的模型。本模型由模型 DiffSynth-Studio/KleinBase4B-i2L-v2 生成

diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d 是 ModelScope 魔搭社区上的 14.7M 参数text-to-image-synthesis模型，采用 Apache License 2.0 许可，基于 black-forest-labs/FLUX.2-klein-base-4B 构建，并支持在线推理（img2img）。

- **Repository**: diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis
- **Parameters**: 14.7M
- **Base model**: black-forest-labs/FLUX.2-klein-base-4B
- **Online inference**: img2img
- **Tags**: LoRA, text-to-image
- **Downloads**: 3
- **Stars**: 0
- **Last updated**: 2026-10-03

Source: https://www.modelscope.cn/models/diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d

---

# 俯瞰、园林、写实

## 模型介绍

本模型由模型 [DiffSynth-Studio/KleinBase4B-i2L-v2](https://modelscope.cn/models/DiffSynth-Studio/KleinBase4B-i2L-v2) 生成

## 推理代码

安装 [DiffSynth-Studio](https://github.com/modelscope/DiffSynth-Studio)：

```bash
pip install diffsynth
```

开始推理：

```python
from diffsynth.pipelines.flux2_image import Flux2ImagePipeline, ModelConfig
import torch

pipe = Flux2ImagePipeline.from_pretrained(
    torch_dtype=torch.bfloat16,
    device="cuda",
    model_configs=[
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="text_encoder/*.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="transformer/*.safetensors"),
        ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="vae/diffusion_pytorch_model.safetensors"),
    ],
    tokenizer_config=ModelConfig(model_id="black-forest-labs/FLUX.2-klein-base-4B", origin_file_pattern="tokenizer/"),
)
pipe.load_lora(pipe.dit, ModelConfig(model_id="diffsynth-i2L-gallery/KleinBase4B-aerialview-garden-photorealistic-dea05d", origin_file_pattern="1791011683.916959-c1341311-21cf-4704-a9fe-046fb9a11266.safetensors"))
prompt = "a cat"
image = pipe(prompt, num_inference_steps=50, cfg_scale=4)
image.save("image.jpg")
```