Haoming02/FIRST
Frame Interpolation Refined with Stable Diffusion via Control Net
When you have video footage where objects move too quickly or the scene changes too drastically, traditional frame interpolation often struggles, leading to blurry or 'ghosting' effects. This project takes your original video frames and any preliminary interpolated frames (like those from Flowframes) and refines the missing frames. It leverages advanced generative AI to create smoother, more coherent transitions, resulting in a cleaner, more professional-looking slow-motion or high-frame-rate video. This is ideal for video editors, animators, or content creators who need to improve the fluidity of their interpolated footage.
No commits in the last 6 months.
Use this if you need to create exceptionally smooth slow-motion or high-frame-rate video from footage where there are significant differences between frames, and existing interpolation tools produce noticeable artifacts.
Not ideal if you are looking for a standalone, all-in-one video editing solution, as this tool focuses specifically on refining pre-interpolated frames.
Stars
24
Forks
4
Language
Python
License
MIT
Category
Last pushed
Jul 05, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/Haoming02/FIRST"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
hnsywangxin/controlnet_stable_tensorrt
stable diffusion, controlnet, tensorrt, accelerate
a-lgil/pose-depot
A collection of ControlNet poses
city96/SD-Latent-Upscaler
Upscaling stable diffusion latents using a small neural network.
camenduru/ControlNet-v1-1-nightly-colab
controlnet v1.1 colab
360CVGroup/RelaCtrl
Efficient controlnet for DiTs