https://github.com/airvitap/diffscaler

A Novel Approach to Video Generation model and their Archives

https://github.com/airvitap/diffscaler

Science Score: 13.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • CITATION.cff file
  • codemeta.json file
    Found codemeta.json file
  • .zenodo.json file
  • DOI references
  • Academic publication links
  • Academic email domains
  • Institutional organization owner
  • JOSS paper metadata
  • Scientific vocabulary similarity
    Low similarity (4.1%) to scientific vocabulary

Keywords

finetuning inference videogeneration videointepolation
Last synced: 6 months ago · JSON representation

Repository

A Novel Approach to Video Generation model and their Archives

Basic Info
  • Host: GitHub
  • Owner: airvitap
  • Default Branch: main
  • Homepage:
  • Size: 7.81 KB
Statistics
  • Stars: 1
  • Watchers: 2
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Topics
finetuning inference videogeneration videointepolation
Created over 2 years ago · Last pushed over 1 year ago
Metadata Files
Readme

README.md

novel-video-synthesis

Base mode

Open Source Video Generation Models to Checkout

  • https://github.com/lichao-sun/Mora
  • https://github.com/G-U-N/AnimateLCM
  • https://github.com/ali-vilab/VGen
  • https://github.com/TIGER-AI-Lab/ConsistI2V
  • https://github.com/showlab/MotionDirector
  • https://github.com/pixeli99/SVD_Xtend
  • https://github.com/Picsart-AI-Research/StreamingT2V
  • https://ecnu-cilab.github.io/ExVideoProjectPage/ (ExVideo is a post-tuning technique aimed at enhancing the capability of video generation models. We have extended Stable Video Diffusion to achieve the generation of long videos up to 128 frames. The)

Miscellaneous Video Generation Models - https://github.com/mbzuai-oryx/Video-LLaVA

References & citations

Spatial & Temporal Transformer - https://research.nvidia.com/labs/toronto-ai/VideoLDM/

https://huggingface.co/hotshotco/Hotshot-XL https://github.com/PKU-YuanGroup/Open-Sora-Plan

ControlNet - https://github.com/lllyasviel/ControlNet

Distributive training - https://huggingface.co/docs/accelerate/

https://github.com/AUTOMATIC1111/stable-diffusion-webui https://github.com/comfyanonymous/ComfyUI https://github.com/facebookresearch/xformers https://github.com/Dao-AILab/flash-attention

FiT: Flexible Vision Transformer for Diffusion Model

SOTA Caption Generation for video : https://github.com/snap-research/Panda-70M https://github.com/willisma/SiT

Unet - https://huggingface.co/docs/diffusers/en/api/loaders/unet - https://paperswithcode.com/method/u-net

https://github.com/Vchitect/Latte

VAE - Consistency Distilled Diff VAE : https://github.com/openai/consistencydecoder

image

AnimateDiff + freeinit - https://github.com/guoyww/animatediff/ - https://dagshub.com/ByteDance/AnimateDiff-Lightning - https://github.com/TianxingWu/FreeInit

Owner

  • Name: AIR Center VIT-AP
  • Login: airvitap
  • Kind: organization
  • Location: India

A public open source github organisation from Artificial Intelligence and Robotics Lab of VIT-AP University , India

GitHub Events

Total
Last Year