---
title: Flux-2-Multi-Angles-LoRA-v2
canonical_url: "https://www.modelscope.cn/models/lovis93/Flux-2-Multi-Angles-LoRA-v2"
md_url: "https://www.modelscope.cn/models/lovis93/Flux-2-Multi-Angles-LoRA-v2.md"
repository: lovis93/Flux-2-Multi-Angles-LoRA-v2
last_updated: 2026-06-16
license: creativeml-openrail-m
pipeline_tag: image-to-image
tasks:
  - image-to-image
base_model:
  - black-forest-labs/FLUX.2-dev
base_model_relation: adapter
parameters: 166.3M
tensor_type:
  - F32
library_name:
  - lora
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
supports_inference: img2img
downloads: 268
stars: 6
tags:
  - flux
  - flux.2
  - flux-lora
  - lora
  - multi-angle
  - camera-angles
  - image-to-image
  - fal-ai
---

# Flux-2-Multi-Angles-LoRA-v2

> Flux-2-Multi-Angles-LoRA-v2 - lovis93 在 ModelScope 开源的模型。🎬 Flux 2 Multi-Angles LoRA v2

lovis93/Flux-2-Multi-Angles-LoRA-v2 是 ModelScope 魔搭社区上的 166.3M 参数image-to-image模型，采用 creativeml-openrail-m 许可，基于 black-forest-labs/FLUX.2-dev 构建，并支持在线推理（img2img）。

- **Repository**: lovis93/Flux-2-Multi-Angles-LoRA-v2
- **License**: creativeml-openrail-m
- **Tasks**: image-to-image
- **Parameters**: 166.3M
- **Base model**: black-forest-labs/FLUX.2-dev
- **Online inference**: img2img
- **Tags**: flux, flux.2, flux-lora, lora, multi-angle, camera-angles, image-to-image, fal-ai
- **Downloads**: 268
- **Stars**: 6
- **Last updated**: 2026-06-16

Source: https://www.modelscope.cn/models/lovis93/Flux-2-Multi-Angles-LoRA-v2

---

# 🎬 Flux 2 Multi-Angles LoRA v2

> **Control camera angles with 72 unique positions - Trained with [fal.ai](https://fal.ai)**

## 🖼️ Results

| Input → Output | Input → Output | Input → Output |
|----------------|----------------|----------------|
| ![Result 1](result01.png) | ![Result 2](result02.png) | ![Result 3](result03.png) |

![72 Poses Demo](poses_72_animated.gif)

---

## 🎯 Prompt Format

```
<sks> [view] [elevation] shot [distance]
```

### Quick Examples

```
<sks> front view eye-level shot close-up
<sks> right side view high-angle shot medium shot
<sks> back view overhead shot wide shot
```

### All 72 Prompts Reference

![72 Poses Prompts](poses_72_prompts.png)

---

## 📦 Files

| File | Use Case |
|------|----------|
| `flux-multi-angles-v2-72poses-fal.safetensors` | [fal.ai](https://fal.ai) |
| `flux-multi-angles-v2-72poses-comfy.safetensors` | ComfyUI |

▶️ [Try it live on fal.ai](https://fal.ai/models/fal-ai/flux-2-lora-gallery/multiple-angles/playground)

---

## ⚙️ Settings

- **LoRA Strength**: 0.8 - 1.0
- **Base Model**: FLUX.2-dev

---

## 📐 72 Camera Positions

**8 Azimuths** × **9 Elevations** × **3 Distances** = **72 Poses**

| Azimuths | Elevations | Distances |
|----------|------------|-----------|
| front, front-right quarter, right side, back-right quarter, back, back-left quarter, left side, front-left quarter | eye-level, low-angle, mid-low, mid-angle, high-mid, high-angle, steep-mid, steep-angle, overhead | close-up, medium, wide |

![Camera Positions](poses_72_hemisphere.png)

---

## 💡 Inspiration

This project was inspired by:
- My previous work [next-scene-qwen-image-lora](https://huggingface.co/lovis93/next-scene-qwen-image-lora-2509)
- [dx8152/Qwen-Edit-2509-Multiple-angles](https://huggingface.co/dx8152/Qwen-Edit-2509-Multiple-angles)

I wanted to document how to properly create a dataset for camera angle control and apply it to Flux.2.

---

## 👤 Author

Created by **[@lovis93](https://huggingface.co/lovis93)** • Trained with [**fal.ai**](https://fal.ai)

**⭐ If you find this useful, please star!**