metadata
library_name: diffusers
pipeline_tag: image-to-image
inference:
parameters:
guidance_scale: 3.5
widget:
- src: example_input.jpg
text: GenEx Panoramic World Initialization
example_title: Panoramic generation from image crop
datasets:
- TaiMingLu/GenEx-DB-Panorama-World
base_model:
- black-forest-labs/FLUX.1-Fill-dev
license: cc-by-4.0
GenEx-World-Initializer 🧭🌍
GenEx World Initializer is panorama generation pipeline built on top of the FluxFillPipeline.
It transforms a single view image into a 360° panoramic image using vision-conditioned inpainting.
- 🖼️ Input: One image (any size, will be center-cropped to square)
- 🧠 Prompt: Optional text to guide panoramic generation
- 🎯 Output: 2048 × 1024 equirectangular image
- 🧩 Mask: Uses a fixed panoramic mask
📦 Usage
from diffusers import DiffusionPipeline
from PIL import Image
import torch
pipe = DiffusionPipeline.from_pretrained(
"genex-world/World-Initializer-image-to-panorama",
custom_pipeline="genex_world_initializer_pipeline",
torch_dtype=torch.bfloat16,
trust_remote_code=True
).to("cuda")
# Load your image (any resolution)
image = Image.open("example_input.jpg")
# Run inference
front_view, output = pipe(image=image)
output.images[0]
🏁 Mask
The following mask is used to train the inpainting diffuser and used to inference automatically.
🔧 Requirements
diffusers>=0.33.1
transformers
numpy
pillow
sentencepiece
✨ BibTex
@misc{lu2025genexgeneratingexplorableworld,
title={GenEx: Generating an Explorable World},
author={Taiming Lu and Tianmin Shu and Junfei Xiao and Luoxin Ye and Jiahao Wang and Cheng Peng and Chen Wei and Daniel Khashabi and Rama Chellappa and Alan Yuille and Jieneng Chen},
year={2025},
eprint={2412.09624},
archivePrefix={arXiv},
primaryClass={cs.CV},
url={https://arxiv.org/abs/2412.09624},
}