---
license: other
license_name: flux-1-dev-non-commercial-license
license_link: https://huggingface.co/black-forest-labs/FLUX.1-dev/blob/main/LICENSE.md
language:
- en
library_name: diffusers
pipeline_tag: text-to-image
base_model: black-forest-labs/FLUX.1-dev
tags:
- diffusers
- lora
- flux
inference:
  parameters:
    width: 1440
    height: 720

---
<Gallery />



# Layerpano3D-FLUX-Panorama-LoRA

<table>
  <tr>
      <td><img src="assets/Magical academy courtyard with floating orbs of light, ancient stone buildings, and a large tree in the center, mystical and enchanting.png" alt="Image 9" width="100%"></td>
        <td><img src="assets/Autumn park scene with people sitting on benches surrounded by colorful trees, storybook illustration style.png" alt="Image 4" width="100%"></td>
    <td><img src="assets/An ancient stone archway standing alone in a peaceful meadow, surrounded by wildflowers, with sunlight streaming through, casting long shadows.png" alt="Image 3" width="100%"></td>
  </tr>
  <tr>
    <td><img src="assets/A charming village market square filled with outdoor vendors, baskets of fresh produce, and villagers interacting in the morning sun.png" alt="Image 2" width="100%"></td>
    <td><img src="assets/A vibrant city avenue, bustling traffic, towering skyscrapers.png" alt="Image 5" width="100%"></td>
    <td><img src="assets/Bustling city street at sunset, skyscrapers, streets, cars.png" alt="Image 6" width="100%"></td>
  </tr>
  <tr>
    <td><img src="assets/Cozy livingroom in christmas.png" alt="Image 7" width="100%"></td>
    <td><img src="assets/lego city with lego shops, lego road with street lamp, cars and lego mans on the street, lego trees and lake at a park.png" alt="Image 8" width="100%"></td>
    <td><img src="assets/A bustling open-air market with colorful stalls overflowing with fresh produce, flowers, and goods, bathed in soft, warm sunlight, capturing the vibrancy of daily life.png" alt="Image 1" width="100%"></td>
  </tr>
</table>

A LoRA model to generate panoramas using Flux (Text2Panorama and Panorama inpaint).

## Which image ratio and resolution to use?

This model has been trained on images with a 2:1 ratio.

[NOTES]: Since we use lora for training, we find that using the same image resolution as training during inference will have better results. We provide lora with multiple resolutions in lora_hubs(now 720×1440 / 512×1024 version1), and will continue to update safetensors with better results and more flexible resolution in the future.

## Inference

```shell
pip install diffusers==0.32.0
```
**Text-to-Panorama Generation** (run with our pipeline_flux.py in repo to ensure the close-loop)
```python
import torch
import random
from pipeline_flux import FluxPipeline # use our modifed flux pipeline to ensure close-loop.

lora_path="lora_hubs/pano_lora_720*1440_v1.safetensors" # download panorama lora in our huggingface repo and replace it to your path.
pipe = FluxPipeline.from_pretrained("black-forest-labs/FLUX.1-dev", torch_dtype=torch.bfloat16).to("cuda")
pipe.load_lora_weights(lora_path) # change this.
pipe.enable_model_cpu_offload()  # save some VRAM by offloading the model to CPU

prompt = 'A vibrant city avenue, bustling traffic, towering skyscrapers'

pipe.enable_vae_tiling()
seed = 119223

#Select the same resolution as LoRA for inference
image = pipe(prompt, 
            height=720,
            width=1440,
            generator=torch.Generator("cpu").manual_seed(seed),
            num_inference_steps=50, 
            blend_extend=6,
            guidance_scale=7).images[0]

image.save("result.png")

```

## Related 360-Panoramic Project
  - [**LayerPano3D**: Layered 3D Panorama for Hyper-Immersive Scene Generation](https://github.com/3DTopia/LayerPano3D). LayerPano3D generates full-view, explorable panoramic 3D scene from a single text prompt.


  - [**Imagine360**: Immersive 360 Video Generation from Perspective Anchor](https://github.com/3DTopia/Imagine360). Imagine360 lifts standard perspective video into 360-degree video with rich and structured motion, unlocking dynamic scene experience from full 360 degrees.


## Non-commercial use

As the base model is FLUX.1-[dev], it should be used for [non-commercial, personal or demonstration purposes only](https://github.com/black-forest-labs/flux/blob/main/model_licenses/LICENSE-FLUX1-dev).

Please use it responsibly, thank you!