Wangt-CN/DisCo issues and pull requests

#100 - A problem about diffusers

Issue - State: closed - Opened by zeezou-isee 2 months ago

#99 - solved

Issue - State: closed - Opened by zeezou-isee 3 months ago

#98 - Typo

Issue - State: open - Opened by eastchun 3 months ago

#97 - drop_pose_ratio is not defined (temporal module finetuning)

Issue - State: open - Opened by eastchun 4 months ago

#96 - 能不能提供多机多卡的运行脚本

Issue - State: open - Opened by gitPZH 4 months ago

#95 - Is the TikTok dataset you provide the MoreTikTok dataset?

Issue - State: open - Opened by Hermine-D 4 months ago

#94 - How to use DeepSpeed for multi-GPU training instead of using mpirun?

Issue - State: open - Opened by wyz12234 4 months ago

#93 - Jimmy

Issue - State: closed - Opened by EdgarGonzalez2784 5 months ago - 1 comment

#92 - None

Issue - State: closed - Opened by eastchun 5 months ago

#91 - jax and jaxlib latest version problem

Issue - State: open - Opened by seyyedAlirezaGhazanfari 5 months ago

#90 - How were these files generated? For validation and training.

Issue - State: open - Opened by xhqi0109 6 months ago

#89 - huggingface demo broken

Issue - State: open - Opened by huangjch526 6 months ago - 1 comment

#88 - “test”

Pull Request - State: closed - Opened by cuiliyuan121 7 months ago

#87 - None

Issue - State: closed - Opened by eastchun 7 months ago

#86 - the code for computing PSNR is wrong

Issue - State: closed - Opened by Delicious-Bitter-Melon 7 months ago - 4 comments

#85 - How can I get "More TikTok-Style Training Data" please?

Issue - State: open - Opened by BugsMaker0513 8 months ago - 1 comment

#84 - [BUG] a bug in the dataset/tiktok_video_dataset.py

Issue - State: open - Opened by ljh0v0 8 months ago

#83 - Questions about image size

Issue - State: open - Opened by ZZfive 8 months ago

#82 - Where can I get the 10K tiktok style test split?

Issue - State: open - Opened by Worromots 8 months ago

#81 - Fix typo from 'eval' to 'val'

Pull Request - State: open - Opened by Fanghaipeng 9 months ago

#80 - how to caculate fvd metrics?

Issue - State: closed - Opened by LucasLOOT 9 months ago - 1 comment

#79 - Error when mpirun -np 3?

Issue - State: closed - Opened by CHNxindong 9 months ago - 2 comments

#78 - Hope for more instruction about the multiple GPU running

Issue - State: closed - Opened by CHNxindong 9 months ago

#77 - Question about the multi-gpu running: 'mpirun -np ...'

Issue - State: closed - Opened by CHNxindong 9 months ago - 7 comments

#76 - Model checkpoint for temporal module

Issue - State: open - Opened by CHNxindong 9 months ago

#75 - Question about the framework

Issue - State: closed - Opened by CHNxindong 9 months ago - 1 comment

#74 - Windows 11 OS

Issue - State: closed - Opened by eastchun 9 months ago - 1 comment

#73 - What is the difference between input image and reference image?

Issue - State: closed - Opened by CHNxindong 9 months ago - 2 comments

#72 - Question about the CLIP encoder and VAE encoder

Issue - State: closed - Opened by CHNxindong 10 months ago - 2 comments

#71 - 'Nan' loss and bad result

Issue - State: open - Opened by 351246241 10 months ago - 1 comment

#70 - About the version incompatibility of the three-party library

Issue - State: closed - Opened by codeayzy 10 months ago

#69 - No access to tiktok checkpoints

Issue - State: open - Opened by JetsettingJames 10 months ago - 3 comments

#68 - Very slow xformers install on the Colab

Issue - State: open - Opened by ShawnFumo 10 months ago - 3 comments

#67 - Cannot download Human_Attribute_Pretrain.tar.gz

Issue - State: closed - Opened by hygenie1228 10 months ago - 1 comment

#66 - How to use the dataset of 512 * 512

Issue - State: open - Opened by MingfuYAN 10 months ago - 4 comments

#65 - No module named 'hjson'

Issue - State: open - Opened by Ishihara-Masabumi 11 months ago - 2 comments

#64 - get wrong result

Issue - State: open - Opened by safehumeng 11 months ago

#63 - Do you have a plan to release the new model weight with temporal modeling?

Issue - State: open - Opened by Delicious-Bitter-Melon 11 months ago - 2 comments

#62 - ControlNet is trained with UNet together?

Issue - State: closed - Opened by KenChen701 11 months ago - 1 comment

#61 - can‘t download pretrained model

Issue - State: closed - Opened by unrealMJ 11 months ago - 1 comment

#60 - CLIP image encoder receive image size as 224*224

Issue - State: closed - Opened by KenChen701 11 months ago - 2 comments

#59 - ModuleNotFoundError: No module named 'deepspeed'

Issue - State: open - Opened by Ishihara-Masabumi 11 months ago

#58 - ERROR 403: Forbidden occurred.

Issue - State: closed - Opened by Ishihara-Masabumi 11 months ago - 3 comments

#57 - about inference

Issue - State: open - Opened by tbxmh 11 months ago

#56 - CLIP image embedding

Issue - State: closed - Opened by soon-yau 11 months ago - 1 comment

#55 - Sample images of demo video request.

Issue - State: open - Opened by yunseongcho 11 months ago - 2 comments

#54 - Have problem with human-specific fine-tuning

Issue - State: closed - Opened by ljh0v0 11 months ago - 1 comment

#53 - Installation instructions don't seem to work for Mac OS with python 3.11, torch versions are not available from pytorch

Issue - State: closed - Opened by frogeyedpeas 12 months ago - 3 comments

#52 - How should I do inference about Human Attribute Pre-training?

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

#51 - Unable to open the Online Gradio Demo

Issue - State: open - Opened by LiuXY3366 12 months ago - 1 comment

#50 - No module named 'torch._six'

Issue - State: closed - Opened by Ishihara-Masabumi 12 months ago - 4 comments

#49 - Problem when training with 4090

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

#48 - Multi-GPU failed to run

Issue - State: closed - Opened by MingfuYAN 12 months ago - 6 comments

#47 - Any way to automatically separate the foreground and background?

Issue - State: closed - Opened by debjit-bw about 1 year ago

#46 - Difficulty finding the inference function

Issue - State: closed - Opened by debjit-bw about 1 year ago - 3 comments

#45 - Human Specific Finetuning

Issue - State: closed - Opened by emcorby2 about 1 year ago - 1 comment

#44 - human_img_edit_gradio.ipynb run error

Issue - State: closed - Opened by bigcornflake about 1 year ago - 1 comment

#43 - How to improve the output resolution?

Issue - State: closed - Opened by lawpdas about 1 year ago

#42 - How can it be successfully run inference on multiple GPUs?

Issue - State: closed - Opened by Delicious-Bitter-Melon about 1 year ago - 1 comment

#41 - LPIPS evaluation should add `normalize=True`

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

#40 - About the reference image

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 1 comment

#39 - Where is pose encoder in code?

Issue - State: closed - Opened by zhangtao22 about 1 year ago

#38 - Composite Caption LineList Creation ?

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

#37 - 如何从你处理好的数据中拿到skeleton中的key points信息？

Issue - State: closed - Opened by Amo5 about 1 year ago - 1 comment

#36 - Video frame 'expand' when performing FVD

Issue - State: closed - Opened by fwbx529 about 1 year ago - 1 comment

#35 - About video frame consistency

Issue - State: closed - Opened by xfguo-ucas about 1 year ago

#34 - About the extra Tiktok-style data

Issue - State: closed - Opened by zehongs about 1 year ago - 1 comment

#33 - deepspeed.runtime.zero.utis.ZeR0RuntimeException

Issue - State: closed - Opened by mumukawayi about 1 year ago - 2 comments

#32 - unexpected_keys when Loaded data from mp_rank_00_model_states.pt

Issue - State: closed - Opened by Daishijun about 1 year ago - 1 comment

#31 - About the training data.

Issue - State: closed - Opened by linziqu about 1 year ago - 2 comments

#30 - No problem now

Issue - State: closed - Opened by fwbx529 about 1 year ago

#29 - why this effect?

Issue - State: closed - Opened by zzk88862 about 1 year ago - 2 comments

#28 - AttributeError: 'DDPMScheduler' object has no attribute 'remove_noise'

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

#27 - Training/Validation Data Split

Issue - State: closed - Opened by Boese0601 about 1 year ago - 6 comments

#26 - About the training data

Issue - State: closed - Opened by XiaoqiangZhou about 1 year ago - 1 comment

#25 - Incorrect FID-VID and FVD

Issue - State: open - Opened by Fanghaipeng about 1 year ago - 15 comments

#24 - for human-specific fine-tuning，I can't execute

Issue - State: open - Opened by zhangtao22 about 1 year ago - 3 comments

#23 - change sd models

Issue - State: open - Opened by silber60 about 1 year ago - 1 comment

#22 - Incorrect parameter name in config scripts

Issue - State: closed - Opened by emcorby2 about 1 year ago - 5 comments

#21 - There is sth wrong with ./annotator/grounded-sam/run.py

Issue - State: open - Opened by zhangtao22 about 1 year ago - 2 comments

#20 - How should I set the learning rate on 8*v100 32g gpus？

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 3 comments

#19 - Why does deepspeed is commented in the finetune file?

Issue - State: closed - Opened by SKBL5694 about 1 year ago - 1 comment

#18 - where is python tool/video/gen_gifs_for_fvd.py？

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 3 comments

#17 - Please fix the command for prerpocessing with Grounded-SAM.

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

#16 - where do these poses come from？./demo_data/pose_img/0049.png","./demo_data/pose_img/0198.png","./demo_data/pose_img/0213.png"

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 1 comment

#15 - How to try demo with my own dataset?

Issue - State: closed - Opened by wnzhyee about 1 year ago - 4 comments

#14 - 'GIT/{:05d}/labels/{:04d}.txt' How to get this file？

Issue - State: closed - Opened by hanhan0521 about 1 year ago - 7 comments

#13 - For hap training, it stopped after step 47999

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 2 comments

#12 - Question about training data structure

Issue - State: closed - Opened by YuanSun-XJTU about 1 year ago - 2 comments

#11 - Some issues about deepspeed

Issue - State: closed - Opened by YuanSun-XJTU about 1 year ago - 6 comments

#10 - support multi-gpus

Issue - State: closed - Opened by NguyenTriTrinh about 1 year ago - 5 comments

#9 - fix typo in process_tsv.py

Pull Request - State: open - Opened by eltociear about 1 year ago

#8 - Human specific finetune

Issue - State: closed - Opened by alicranck about 1 year ago - 6 comments

#7 - OSError: We couldn't connect to 'https://huggingface.co' to load this model, couldn't find it in the cached files and it looks like /home1/wangtan/code/ms_internship2/github_repo/run_test/diffusers/sd-image-variations-diffusers is not the path to a directory containing a scheduler_config.json file. Checkout your internet connection or see how to run the library in offline mode at 'https://huggingface.co/docs/diffusers/installation#offline-mode'.

Issue - State: closed - Opened by zhangtao22 about 1 year ago - 6 comments

#6 - Pre-training dataset

Issue - State: closed - Opened by dongbo811 about 1 year ago - 1 comment

#5 - About BatchSize in Fine-tuning with Disentangled Control

Issue - State: closed - Opened by Fanghaipeng about 1 year ago - 3 comments

#4 - About openpose and inference code

Issue - State: closed - Opened by anhquannguyen21 about 1 year ago - 2 comments

GitHub / Wangt-CN/DisCo issues and pull requests