JIA-Lab-research/Video-P2P
Video-P2P: Video Editing with Cross-attention Control
This tool helps video editors and content creators modify existing video footage by changing elements within the scene using text prompts. You input an existing video and a textual description of the desired change (e.g., 'a rabbit jumping' becomes 'a penguin running'), and it outputs a new video with that alteration integrated seamlessly. Anyone involved in video production, digital art, or marketing who needs to quickly iterate on video concepts without complex manual editing would find this useful.
426 stars. No commits in the last 6 months.
Use this if you need to quickly swap subjects, objects, or even stylistic elements in a video using simple text descriptions, without needing advanced video editing software skills.
Not ideal if you need to make precise frame-by-frame edits, complex visual effects, or manipulate video elements beyond what can be described with a text prompt.
Stars
426
Forks
27
Language
Python
License
—
Category
Last pushed
Jun 30, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/JIA-Lab-research/Video-P2P"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hao-ai-lab/FastVideo
A unified inference and post-training framework for accelerated video generation.
ModelTC/LightX2V
Light Image Video Generation Inference Framework
thu-ml/TurboDiffusion
TurboDiffusion: 100–200× Acceleration for Video Diffusion Models
PKU-YuanGroup/Helios
Helios: Real Real-Time Long Video Generation Model
PKU-YuanGroup/MagicTime
[TPAMI 2025🔥] MagicTime: Time-lapse Video Generation Models as Metamorphic Simulators