AlonzoLeeeooo/StableV2V
The official implementation of the paper titled "StableV2V: Stablizing Shape Consistency in Video-to-Video Editing".
StableV2V helps video editors and content creators modify videos while keeping object shapes consistent, even with significant visual changes. You provide an existing video and a prompt (like a sketch or text description), and it outputs an edited video where the altered objects maintain their original proportions and form across frames. This tool is for anyone creating visual content who needs to manipulate video elements without distortion.
168 stars.
Use this if you need to edit specific elements within a video, like changing an object's style or filling in missing parts, and want to ensure the edited object looks natural and doesn't warp or flicker across frames.
Not ideal if your main goal is basic video cuts, transitions, or color correction, as this tool is focused specifically on advanced, shape-preserving content manipulation.
Stars
168
Forks
6
Language
Python
License
MIT
Category
Last pushed
Dec 11, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/AlonzoLeeeooo/StableV2V"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...