JiangkaiWu/Promptus
Official impl. of AAAI Oral Paper "Promptus: Can Prompts Streaming Replace Video Streaming with Stable Diffusion". A general semantic video communication framework.
This project helps video streaming providers and network engineers deliver high-quality video with less network bandwidth. It takes an existing video, converts it into a compact series of 'prompts,' and then uses these prompts to reconstruct a visually similar video on the viewer's device. This is ideal for anyone looking to reduce the data load of video content while maintaining a good user experience.
Use this if you are a video streaming service provider or network engineer aiming to optimize video delivery over constrained network conditions.
Not ideal if your primary goal is basic video playback without concerns for network efficiency or if you lack access to GPU resources for real-time generation.
Stars
77
Forks
6
Language
Python
License
Apache-2.0
Category
Last pushed
Feb 26, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JiangkaiWu/Promptus"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
philz1337x/clarity-upscaler
Clarity AI | AI Image Upscaler & Enhancer - free and open-source Magnific Alternative
wfjsw/danbooru-diffusion-prompt-builder
Danbooru / NovelAI 标签超市
kaihsu0327/ai-image-upscaler
🤖 Enhance your images effortlessly with AI-powered upscaling using Real-ESRGAN in this...
jhc13/taggui
Tag manager and captioner for image datasets
jamesmoore/SDMeta
Extract SD (Automatic1111, ComfyUI) metadata from generated files in bulk, search and browse your prompts