pmh9960/SphereDiff
Official PyTorch implementation of "SphereDiff: Tuning-free Omnidirectional Panoramic Image and Video Generation via Spherical Latent Representation"
This tool helps you create seamless 360-degree panoramic images and videos without distortions, using simple text descriptions as input. You can generate static immersive environments or dynamic scenes that look great from any viewing angle. It's ideal for creators, designers, and virtual reality content developers who need high-quality, full-sphere visual assets.
Use this if you need to quickly generate immersive 360-degree images or short videos for virtual tours, architectural visualizations, or VR/AR experiences from text prompts.
Not ideal if you require fine-grained control over specific objects within the generated scene or need to edit existing panoramic content rather than create new ones.
Stars
50
Forks
3
Language
Python
License
—
Category
Last pushed
Feb 09, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/pmh9960/SphereDiff"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
cswry/SeeSR
[CVPR2024] SeeSR: Towards Semantics-Aware Real-World Image Super-Resolution
JJLibra/SALAD-Pan
🤗 Official implementation for "SALAD-Pan: Sensor-Agnostic Latent Adaptive Diffusion for...
open-mmlab/mmgeneration
MMGeneration is a powerful toolkit for generative models, based on PyTorch and MMCV.
Janspiry/Image-Super-Resolution-via-Iterative-Refinement
Unofficial implementation of Image Super-Resolution via Iterative Refinement by Pytorch
hanjq17/Spectrum
[CVPR 2026] Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration