Aller au contenu
ModelPrésentéExterne
Télécharger

World Initializer Image To Panorama

GenEx World Initializer is panorama generation pipeline built on top of the FluxFillPipeline.

TypeModèleModèle de baseblack-forest-labs/FLUX.1-Fill-devVersionRevision bdf9a02BClasse

Source du modèle

Type
Modèle
Taille du fichier
160 MB–9,30 GB
Modèle de base
black-forest-labs/FLUX.1-Fill-dev
Version
vRevision bdf9a02
Mis à jour
6 oct. 2026
Téléchargements
56
Source
Hugging Face

Description de la source

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}, 
}

Exigences

Modèles

1

Sources

1 source
Hugging FacePrincipalVersion bdf9a02257c4c2728bcd90404d53687a9641e205
huggingface.co/genex-world/World-Initializer-image-to-panorama/tree/bdf9a02257c4c2728bcd90404d53687a9641e205

Vérifié 6 oct.

Artefacts du modèle

7 artefacts

text_encoder_2/model-00001-of-00002.safetensors

safetensors · 4,65 GB · SHA-256 ec87bffd1923…893e · Hugging Face

Télécharger

text_encoder_2/model-00002-of-00002.safetensors

safetensors · 4,22 GB · SHA-256 a5640855b301…da00 · Hugging Face

Télécharger

text_encoder/model.safetensors

safetensors · 235 MB · SHA-256 893d67a23f46…d082 · Hugging Face

Télécharger

transformer/diffusion_pytorch_model-00001-of-00003.safetensors

safetensors · 9,30 GB · SHA-256 cfaf8fec448f…da0b · Hugging Face

Télécharger

transformer/diffusion_pytorch_model-00002-of-00003.safetensors

safetensors · 9,27 GB · SHA-256 35a81003fdc8…58c2 · Hugging Face

Télécharger

transformer/diffusion_pytorch_model-00003-of-00003.safetensors

safetensors · 3,60 GB · SHA-256 c6f7c82ed67d…a5c4 · Hugging Face

Télécharger

vae/diffusion_pytorch_model.safetensors

safetensors · 160 MB · SHA-256 f5b59a268515…40a3 · Hugging Face

Télécharger

Extraits de sources

3 extraits

--- 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](https://huggingface.co/black-forest-labs/FLUX.1-Fill-dev). 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 ![](examples.png) ## 📦 Usage ```python 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. ![](pano_mask.png) ## 🔧 Requirements ```txt 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}, } ```

Source context: 56 downloads · 8 likes · Pipeline image-to-image · Library diffusers · Repo genex-world/World-Initializer-image-to-panorama

Source context: 77 downloads · 8 likes · Pipeline image-to-image · Library diffusers · Repo genex-world/World-Initializer-image-to-panorama