Infinite-Forcing: Towards Infinite-Long Video Generation

Make self forcing endless. Add cache purging. Add prompt controllability.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

Adding a quadruped pose control model to ControlNet!

LocalHost of PIA in Windows

WebUI extension for ControlNet

AnimateDiff I2V version.

animatediff prompt travel

Official implementation of the paper "Improving Sample Quality of Diffusion Models Using Self-Attention Guidance" (ICCV 2023)

resources for creating Ininite zoom video using Stable Diffiusion, you can use multiple prompts and it is easy to use.

Photo Wake-Up: 3D Character Animation from a Single Photo

Use Runway's Stable-diffusion inpainting model to create an infinite loop video. Inspired by https://twitter.com/matthen2/status/1564608773485895692

Forked version of AnimateDiff, attempts to add init images. If you are look into original repo, please go to https://github.com/guoyww/animatediff/

Stable diffusion for inpainting

Added Gradio UI to accompany "A Method for Animating Children's Drawings of the Human Figure"

Diffusers Stable Diffusion as a Cog model

深度学习500问，以问答形式对常用的概率知识、线性代数、机器学习、深度学习、计算机视觉等热点问题进行阐述，以帮助自己及有需要的读者。 全书分为18个章节，近30万字。由于水平有限，书中不妥之处恳请广大读者批评指正。 未完待续............ 如有意合作，联系scutjy2015@163.com 版权所有，违权必究 Tan 2018.06

[ECCV 2020] Flow-edge Guided Video Completion

StyleGAN Encoder - converts real images to latent space

Image Completion using PatchMatch algorithm