Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / lucidrains/video-diffusion-pytorch issues and pull requests

#38 - Text and video training

Issue - State: open - Opened by zzzbbt 6 months ago

#36 - Update README.md to add sampling code snippet

Pull Request - State: open - Opened by chpk 10 months ago

#35 - Problem about cond_scale

Issue - State: closed - Opened by kanydao 12 months ago - 2 comments

#34 - Any one get any video result by training this project?

Issue - State: open - Opened by double-fire-0 about 1 year ago - 6 comments

#33 - can't run the code

Issue - State: open - Opened by Zyj1moreT about 1 year ago - 1 comment

#32 - Update setup.py - Fixed broken installation due to forgotten comma

Pull Request - State: closed - Opened by xaf-cv about 1 year ago

#31 - Add missing requirements for conditional generation

Pull Request - State: closed - Opened by kkedich about 1 year ago - 4 comments

#30 - Why SpatialLinearAttention use k mul v first?

Issue - State: open - Opened by TtuHamg about 1 year ago

#29 - Inferencing on a custom .gif after training the model

Issue - State: closed - Opened by chpk over 1 year ago - 2 comments

#28 - Images are 2-D, how to adapt this for 1-D data ?

Issue - State: open - Opened by mayank64ce over 1 year ago - 4 comments

#27 - #after a lot of training

Issue - State: open - Opened by MehdiGhorb over 1 year ago - 2 comments

#26 - video prediction

Issue - State: open - Opened by XXinLiu over 1 year ago - 3 comments

#25 - What is this structure?

Issue - State: open - Opened by jacob-kang over 1 year ago

#24 - Class conditioned training

Issue - State: open - Opened by Indra24710 almost 2 years ago

#23 - Groupnorm is not factorised across time?

Issue - State: open - Opened by huddyyeo almost 2 years ago

#22 - Where is the output saved if running in google collab?

Issue - State: open - Opened by jackson-sandland almost 2 years ago

#21 - why the code has two versions of spitial transformer?

Issue - State: open - Opened by diaodeyi about 2 years ago

#20 - Implementation of reconstruction-guided sampling in VDM

Issue - State: open - Opened by wenyihong about 2 years ago - 2 comments

#19 - Is there any pertrained model?

Issue - State: open - Opened by diaodeyi about 2 years ago - 2 comments

#18 - result rendering

Issue - State: open - Opened by farhad-abdi about 2 years ago - 1 comment

#15 - Elucidated version

Issue - State: closed - Opened by liangbingzhao over 2 years ago - 1 comment

#14 - the commitment: one more residual

Issue - State: closed - Opened by liangbingzhao over 2 years ago - 26 comments

#13 - Noisy output & "text_use_bert_cls" error

Issue - State: open - Opened by GoutamKelam over 2 years ago - 31 comments

#12 - Reason for combining rotary and relative positional embedding?

Issue - State: open - Opened by oxjohanndiep over 2 years ago - 1 comment

#11 - Duplicate dividing in relative positional encoding

Issue - State: open - Opened by SongweiGe over 2 years ago - 1 comment

#9 - Gradient method for conditional sampling

Issue - State: open - Opened by LuckyDC over 2 years ago - 4 comments

#8 - related recent work

Issue - State: open - Opened by rom1504 over 2 years ago - 1 comment

#7 - Conditioning on image + text embedding

Issue - State: open - Opened by ChintanTrivedi over 2 years ago - 4 comments

#6 - attn mask suppose be `~mask`

Issue - State: closed - Opened by CiaoHe over 2 years ago - 2 comments

#5 - Training Dataset

Issue - State: open - Opened by Mq-Zhang1 almost 3 years ago - 2 comments

#4 - Generating longer videos at test time

Issue - State: open - Opened by mrkulk almost 3 years ago - 46 comments

#3 - Unconditioned UNet

Issue - State: closed - Opened by shehan360 almost 3 years ago - 1 comment

#2 - How to save a video？

Issue - State: closed - Opened by 980202006 almost 3 years ago - 8 comments

#1 - Just want to say this looks exciting!

Issue - State: closed - Opened by Mut1nyJD almost 3 years ago - 1 comment