0606zt/PanoLlama
[ICCV 2025 Highlight] Panorama Generation as a Next-Token Prediction Task.
PanoLlama helps designers, artists, and photographers create expansive and seamless panoramic images. You provide a text description or an existing image, and it generates incredibly wide, coherent panoramas that can expand endlessly. This tool is for anyone needing to visualize vast scenes or produce compelling visual assets for marketing, creative projects, or virtual environments.
Use this if you need to generate high-quality, continuous panoramic images from text prompts or existing images, with advanced control over layout and scale.
Not ideal if you're looking for a simple, one-click panorama stitcher for personal photos without needing advanced generative capabilities or control.
Stars
48
Forks
—
Language
Python
License
—
Category
Last pushed
Oct 29, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/transformers/0606zt/PanoLlama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TinyLLaVA/TinyLLaVA_Factory
A Framework of Small-scale Large Multimodal Models
zjunlp/EasyInstruct
[ACL 2024] An Easy-to-use Instruction Processing Framework for LLMs.
rese1f/MovieChat
[CVPR 2024] MovieChat: From Dense Token to Sparse Memory for Long Video Understanding
haotian-liu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
NVlabs/Eagle
Eagle: Frontier Vision-Language Models with Data-Centric Strategies