---
title: flux-2-klein-4b-spritesheet-lora
canonical_url: "https://www.modelscope.cn/models/AI-ModelScope/flux-2-klein-4b-spritesheet-lora"
md_url: "https://www.modelscope.cn/models/AI-ModelScope/flux-2-klein-4b-spritesheet-lora.md"
repository: AI-ModelScope/flux-2-klein-4b-spritesheet-lora
last_updated: 2026-06-16
license: apache-2.0
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.2-klein-4B
base_model_relation: adapter
parameters: 38.0M
tensor_type:
  - F32
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
supports_inference: img2img
downloads: 116
stars: 0
tags:
  - flux
  - flux-2-klein
  - flux-lora
  - lora
  - sprite-sheet
  - game-asset
  - 2x2-grid
  - multi-view
  - isometric
  - top-down
  - side-view
  - image-to-image
  - fal-ai
  - "template:diffusion-lora"
---

# flux-2-klein-4b-spritesheet-lora

> flux-2-klein-4b-spritesheet-lora - AI-ModelScope 在 ModelScope 开源的模型。🎮 Flux 2×2 Sprite Sheet LoRA

AI-ModelScope/flux-2-klein-4b-spritesheet-lora 是 ModelScope 魔搭社区上的 38.0M 参数image-to-image模型，采用 apache-2.0 许可，基于 black-forest-labs/FLUX.2-klein-4B 构建，并支持在线推理（img2img）。

- **Repository**: AI-ModelScope/flux-2-klein-4b-spritesheet-lora
- **License**: apache-2.0
- **Tasks**: image-to-image
- **Parameters**: 38.0M
- **Base model**: black-forest-labs/FLUX.2-klein-4B
- **Online inference**: img2img
- **Tags**: flux, flux-2-klein, flux-lora, lora, sprite-sheet, game-asset, 2x2-grid, multi-view, isometric, top-down, side-view, image-to-image, fal-ai, template:diffusion-lora
- **Downloads**: 116
- **Stars**: 0
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/AI-ModelScope/flux-2-klein-4b-spritesheet-lora

---

<Gallery />

<div align="center">

# 🎮 Flux 2×2 Sprite Sheet LoRA

### Transform any object into a **2×2 multi-view sprite sheet** with consistent style

[![Try on fal.ai](https://img.shields.io/badge/🚀_Try_it_Live-fal.ai-FF6B35?style=for-the-badge)](https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora?share=011c2b51-6705-4344-9aa4-73b8df660bbc)
[![License](https://img.shields.io/badge/License-Apache_2.0-green?style=for-the-badge)](https://opensource.org/licenses/Apache-2.0)

<img src="images/banner.png" alt="Sprite Sheet LoRA Banner" width="100%">

</div>

---

## 🎯 What does this model do?

This LoRA transforms **any single object image** into a professional **2×2 sprite sheet** with 4 different camera angles:
```
┌────────────────────┬────────────────────┐
│    ISOMETRIC ↘     │    ISOMETRIC ↙     │
│  Front-right view  │  Front-left view   │
├────────────────────┼────────────────────┤
│    SIDE VIEW ←     │    TOP-DOWN ↑      │
│  Profile from left │  Bird's eye view   │
└────────────────────┴────────────────────┘
```

Perfect for **game developers**, **asset creators**, and **3D artists** who need consistent multi-view references.

---

## 🖼️ Examples

<table>
<tr>
<th>Input</th>
<th>Output (2×2 Sprite Sheet)</th>
</tr>
<tr>
<td><img src="examples/jet_fighter_input.png" width="300"></td>
<td><img src="examples/jet_fighter_output.png" width="300"></td>
</tr>
<tr>
<td><img src="examples/biplane_input.png" width="300"></td>
<td><img src="examples/biplane_output.png" width="300"></td>
</tr>
<tr>
<td><img src="examples/sports_car_input.png" width="300"></td>
<td><img src="examples/sports_car_output.png" width="300"></td>
</tr>
<tr>
<td><img src="examples/armored_car_input.png" width="300"></td>
<td><img src="examples/armored_car_output.png" width="300"></td>
</tr>
</table>

---

## 🚀 Quick Start

| Parameter | Value |
|-----------|-------|
| **Prompt** | `2x2 sprite sheet` |
| **Recommended LoRA Scale** | `1.1` |

---

## 💻 Usage

### Try it Live on fal.ai

▶️ **[Open Playground](https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora?share=011c2b51-6705-4344-9aa4-73b8df660bbc)**

### With fal.ai SDK
```python
import fal_client

def on_queue_update(update):
    if isinstance(update, fal_client.InProgress):
        for log in update.logs:
           print(log["message"])

result = fal_client.subscribe(
    "fal-ai/flux-2-klein/4b/base/edit/lora",
    arguments={
        "prompt": "2x2 sprite sheet",
        "model_name": None,
        "loras": [{
            "path": "https://huggingface.co/fal/flux-2-klein-4b-spritesheet-lora/resolve/main/flux-spritesheet-lora.safetensors",
            "scale": 1.1
        }],
        "embeddings": [],
        "image_urls": ["https://your-image-url.png"]
    },
    with_logs=True,
    on_queue_update=on_queue_update,
)
print(result)
```

---

## 📐 Output Layout

The model produces a **2×2 grid** with these specific views:

| Position | View Type | Direction |
|----------|-----------|-----------|
| **Top-Left** | Isometric 3/4 | Object faces bottom-right ↘ |
| **Top-Right** | Isometric 3/4 | Object faces bottom-left ↙ |
| **Bottom-Left** | Side Profile | Object faces left ← |
| **Bottom-Right** | Top-Down | Object faces up ↑ |

> All 4 views maintain the same art style, colors, and proportions.

---

## 🎨 About the Red Background

The output uses a **consistent red background** by design. This solid color background:
- Improves style consistency across all 4 views
- Makes it easy to remove the background for game integration
- Ensures clean edges for sprite extraction

---

## 📦 Model Files

| File | Use Case |
|------|----------|
| `flux-spritesheet-lora.safetensors` | fal.ai |
| `mFtSubaAlDqtHyKk6eIPi_pytorch_lora_weights_comfy_converted.safetensors` | ComfyUI |

---

## 🎓 Training Details

<details>
<summary>Click to expand</summary>

### Dataset
- **Size**: 48 curated sprite sheet pairs (from 120 generated, manually validated)
- **Content**: Diverse vehicle and object categories including:
  - **Aircraft**: jet fighters, helicopters, biplanes, cargo planes, drones, zeppelins
  - **Military Vehicles**: tanks, APCs, artillery, humvees, missile launchers
  - **Civilian Vehicles**: sports cars, motorcycles, trucks, buses, bicycles
  - **Construction Equipment**: excavators, bulldozers, cranes, forklifts
  - **Trains**: locomotives, bullet trains, freight trains, trams
  - **Ships & Boats**: battleships, submarines, yachts, speedboats, kayaks
  - **Space & Sci-Fi**: rockets, space shuttles, mechs, hover vehicles, UFOs
- **Style**: Game-ready 2D assets with red background for consistency
- **Validation**: AI-validated for correct view orientations, then manually curated

### Training
- **Base Model**: FLUX.2-Klein 4B
- **Platform**: [fal.ai](https://fal.ai)
- **Method**: LoRA training

</details>

---

## 🎮 Use Cases

- **Game Development**: Generate sprite sheets for 2D/isometric games
- **Asset Creation**: Quick multi-view references for 3D modeling

---

## ⚠️ Limitations

- Output background is solid red (by design, for consistency)

---

## 📄 License

[Apache 2.0](https://opensource.org/licenses/Apache-2.0)

---

<div align="center">

### Created by [@ilkerzgi](https://huggingface.co/ilkerzgi) • Trained with [fal.ai](https://fal.ai)


[![Try on fal.ai](https://img.shields.io/badge/🚀_Try_it_Live-fal.ai-FF6B35?style=for-the-badge)](https://fal.ai/models/fal-ai/flux-2/klein/4b/base/edit/lora?share=011c2b51-6705-4344-9aa4-73b8df660bbc)

</div>
