Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / Vchitect/Latte issues and pull requests
#100 - T2V training and evaluation
Issue -
State: closed - Opened by yizenghan about 2 months ago
- 7 comments
Labels: question, automatic-stale, automatic-closing
#99 - inference memory with torch.set_grad_enabled(True)
Issue -
State: closed - Opened by pwwwyyy 2 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#98 - Is there tutorial on transfering t2i to t2v model?
Issue -
State: closed - Opened by foreverpiano 2 months ago
- 5 comments
Labels: duplicate, automatic-stale, automatic-closing
#97 - FVD on UCF-101
Issue -
State: closed - Opened by yizenghan 2 months ago
- 15 comments
Labels: question
#96 - delete unuse codes
Pull Request -
State: closed - Opened by xinzzzhou 2 months ago
#95 - How can I utilize the weights of pre-trained PixArt-α to initialize the parameters of the spatial Transformer block in the Latte T2V model?
Issue -
State: closed - Opened by g-makerr 2 months ago
- 2 comments
Labels: question
#94 - Evaluate the `FVD` on FFS
Issue -
State: closed - Opened by zhang-haojie 2 months ago
- 4 comments
Labels: question
#93 - Can we use batch_size>1 in sample_t2x.py
Issue -
State: closed - Opened by foreverpiano 2 months ago
- 7 comments
Labels: question, automatic-stale
#92 - what the param <input_sq_size> stands for?
Issue -
State: closed - Opened by leonardodora 3 months ago
- 2 comments
Labels: question
#91 - Batch Size Ablations
Issue -
State: closed - Opened by fan23j 3 months ago
- 1 comment
Labels: question
#90 - Can Latte train for I2V tasks?
Issue -
State: closed - Opened by 0Godness 4 months ago
- 2 comments
Labels: enhancement
#89 - Update environment.yml
Pull Request -
State: closed - Opened by Upper9527 4 months ago
#88 - Update pipeline_videogen.py
Pull Request -
State: closed - Opened by Upper9527 4 months ago
#87 - Update train.py
Pull Request -
State: closed - Opened by Upper9527 4 months ago
#86 - Update latte.py
Pull Request -
State: closed - Opened by Upper9527 4 months ago
#85 - Update environment.yml
Pull Request -
State: closed - Opened by Upper9527 4 months ago
#84 - 模型在ucf101上无法收敛
Issue -
State: closed - Opened by renyuanzhe 4 months ago
- 5 comments
Labels: duplicate, automatic-stale
#83 - Any plan to implement Latte in HuggingFace's diffusers library?
Issue -
State: closed - Opened by Quest4AiJ 4 months ago
- 3 comments
Labels: enhancement
#82 - How to get preprocessed_ffs
Issue -
State: closed - Opened by zhang-haojie 4 months ago
- 4 comments
Labels: duplicate
#81 - Error once speed up training
Issue -
State: closed - Opened by moeinheidari7829 4 months ago
- 2 comments
Labels: enhancement
#80 - Question: evaluate the FVD
Issue -
State: closed - Opened by Alienge 4 months ago
- 6 comments
Labels: question
#79 - the code of variant 4
Issue -
State: closed - Opened by pangpangjy 4 months ago
- 1 comment
Labels: enhancement, automatic-stale
#78 - how to place and preprocess these datasets
Issue -
State: closed - Opened by renyuanzhe 5 months ago
- 7 comments
Labels: question, automatic-stale
#77 - Question: model code and design choices
Issue -
State: closed - Opened by mrartemevmorphic 5 months ago
- 2 comments
Labels: question, automatic-stale
#76 - 视频帧率
Issue -
State: closed - Opened by fenghe12 5 months ago
- 2 comments
Labels: question, automatic-stale
#75 - question on t2v model training
Issue -
State: closed - Opened by diffusion-lover 5 months ago
- 2 comments
Labels: question, automatic-stale
#74 - 有关时长的问题。
Issue -
State: closed - Opened by LinQianhe02grey 5 months ago
- 4 comments
Labels: question, automatic-stale
#73 - About video VAE
Issue -
State: closed - Opened by Darius-H 5 months ago
- 2 comments
Labels: question, automatic-stale
#72 - Questions about the *0.18215 and /0.18215 operation
Issue -
State: closed - Opened by haibao-yu 5 months ago
- 2 comments
#71 - Is autoregression possible?
Issue -
State: closed - Opened by zhaohm14 5 months ago
- 3 comments
Labels: enhancement, automatic-stale
#70 - No positional embeddings in LatteT2V?
Issue -
State: closed - Opened by DanielSHKao 5 months ago
#69 - fix xformer input shape of Q,K,V in latte.py
Pull Request -
State: closed - Opened by tianyma 6 months ago
- 1 comment
#68 - [Feature] WIP: support sequence parallel
Pull Request -
State: open - Opened by HIT-cwh 6 months ago
Labels: enhancement
#67 - FaceForensics数据集
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 3 comments
Labels: question, automatic-stale
#66 - Some weights of AutoencoderKL were not initialized from the model checkpoint at /path/to/Latte/t2v_required_models/ and are newly initialized because the shapes did not match:
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 3 comments
Labels: duplicate, automatic-stale
#65 - Evaluate the FVD?
Issue -
State: closed - Opened by huangjch526 6 months ago
- 5 comments
Labels: duplicate
#64 - CUDA out of memory
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 6 comments
Labels: question, automatic-stale, automatic-closing
#63 - Fix typo
Pull Request -
State: closed - Opened by AlonzoLeeeooo 6 months ago
#62 - image_size = [256,512]
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 4 comments
Labels: question
#61 - RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 2 comments
#60 - RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'
Issue -
State: closed - Opened by likeatingcake 6 months ago
- 2 comments
Labels: duplicate, automatic-stale, automatic-closing
#59 - What is the difference between Latte and ViViT?
Issue -
State: closed - Opened by Leeeshuz 6 months ago
- 3 comments
Labels: question, automatic-stale, automatic-closing
#58 - trained and sample result very strange (我自己训练复现的效果很奇怪)
Issue -
State: closed - Opened by huangjch526 6 months ago
- 21 comments
Labels: question
#57 - Why choose these datasets and why not compare with pika, SVD or Gen2?
Issue -
State: closed - Opened by qiuhaining 6 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#56 - Extra key in ucf101.pt
Issue -
State: closed - Opened by wang-muhan 6 months ago
- 8 comments
Labels: question, automatic-stale, automatic-closing
#55 - About resume checkpoint
Issue -
State: closed - Opened by kaiw7 7 months ago
- 3 comments
Labels: question, automatic-stale, automatic-closing
#54 - About Training Speed
Issue -
State: closed - Opened by ZekaiGalaxy 7 months ago
- 6 comments
Labels: question, automatic-stale, automatic-closing
#53 - diffusion noise modify
Issue -
State: closed - Opened by ErwinKC 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#52 - Implementation of compression frame patch embedding (Fig. 3b)
Issue -
State: closed - Opened by paulchhuang 7 months ago
- 2 comments
Labels: enhancement
#51 - Option to use ReBased Linear Attention and RingAttention
Pull Request -
State: open - Opened by kabachuha 7 months ago
- 3 comments
Labels: enhancement
#50 - t2v只支持16帧吗?我改成更多比如32帧就啥都看不到了
Issue -
State: closed - Opened by epcsoft 7 months ago
- 2 comments
Labels: enhancement, automatic-stale, automatic-closing
#49 - 如何复现主页展示的t2v效果?
Issue -
State: closed - Opened by HRain1016 7 months ago
- 4 comments
Labels: question, automatic-stale, automatic-closing
#48 - Train code of t2v?
Issue -
State: closed - Opened by kings-rgb 7 months ago
- 7 comments
Labels: question, automatic-stale, automatic-closing
#47 - About evaluation
Issue -
State: closed - Opened by kaiw7 7 months ago
- 4 comments
Labels: question, automatic-stale, automatic-closing
#46 - t2i代码疑问
Issue -
State: closed - Opened by LiuhanChen-github 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#45 - anyone meet zero grad?零梯度?
Issue -
State: closed - Opened by huangjch526 7 months ago
- 1 comment
Labels: question
#44 - Code Reuse
Issue -
State: closed - Opened by LinB203 7 months ago
- 6 comments
Labels: question, automatic-stale, automatic-closing
#43 - how to get 2048 videos for computing FVD?
Issue -
State: closed - Opened by hdjsjyl 7 months ago
- 4 comments
Labels: help wanted, automatic-stale, automatic-closing
#42 - How can I turn on the autoregressive mode to generate >16 frame videos?
Issue -
State: closed - Opened by luweiblues 7 months ago
- 2 comments
Labels: help wanted, automatic-stale, automatic-closing
#41 - 为什么会这样报错呢在运行sample.py模块的时候Traceback (most recent call last): File "C:\Users\Dell\Desktop\Project\Latte-main\sample\sample.py", line 29, in <module> from models import get_models File "C:\Users\Dell\Desktop\Project\Latte-main\models\__init__.py", line 7, in <module> from .latte_t2v import LatteT2V File "C:\Users\Dell\Desktop\Project\Latte-main\models\latte_t2v.py", line 11, in <module> from diffusers.models.embeddings import get_1d_sincos_pos_embed_from_grid, ImagePositionalEmbeddings, CaptionProjection, PatchEmbed, CombinedTimestepSizeEmbeddings ImportError: cannot import name 'CaptionProjection' from 'diffusers.models.embeddings'
Issue -
State: closed - Opened by counwakd 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#40 - Update ucf101_image_datasets.py
Pull Request -
State: closed - Opened by xszheng2020 7 months ago
- 2 comments
#39 - Training BatchSize
Issue -
State: closed - Opened by ZekaiGalaxy 7 months ago
- 6 comments
Labels: question, automatic-stale, automatic-closing
#38 - Issue about "LayerNormKernelImpl" not implemented for 'Half'
Issue -
State: closed - Opened by kaiw7 7 months ago
- 5 comments
#37 - Can you provide the code for DDIM sampler
Issue -
State: closed - Opened by lcwLcw123 7 months ago
- 1 comment
Labels: enhancement
#36 - Re-implementation err on ffs experiment
Issue -
State: closed - Opened by dummy702 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#35 - Preprocess of UCF101
Issue -
State: closed - Opened by valencebond 7 months ago
- 15 comments
Labels: question, automatic-stale, automatic-closing
#34 - Non-consecutive added token '<extra_id_99>' found.
Issue -
State: closed - Opened by heatingma 7 months ago
- 2 comments
#33 - torchrun --nnodes=1 --nproc_per_node=2 train_with_img.py --config ./configs/sky/sky_img_train.yaml error
Issue -
State: closed - Opened by dpyneo 7 months ago
- 3 comments
Labels: question, automatic-stale, automatic-closing
#32 - Discriminative tasks
Issue -
State: closed - Opened by bhack 7 months ago
- 2 comments
Labels: question, automatic-stale
#31 - Cannot find model:LatteT2V.from_pretrained_2d
Issue -
State: closed - Opened by bosima 7 months ago
- 1 comment
#30 - What is
Issue -
State: closed - Opened by olliacc 7 months ago
- 3 comments
Labels: question, automatic-stale, automatic-closing
#29 - Does Latte support multiple GPUs
Issue -
State: closed - Opened by afezeriaWrnbbmm 7 months ago
- 4 comments
#28 - Latte的实时微信讨论组
Issue -
State: closed - Opened by akebest 7 months ago
- 7 comments
Labels: enhancement, automatic-stale, automatic-closing
#27 - run bash sample/t2v.sh error
Issue -
State: closed - Opened by afezeriaWrnbbmm 7 months ago
- 4 comments
#26 - Excellent work, will there be an official support of images to vedio (like sora) ?
Issue -
State: closed - Opened by jeffchy 7 months ago
- 5 comments
Labels: enhancement, automatic-stale, automatic-closing
#25 - T2V with >16 vedio_length output random noises
Issue -
State: closed - Opened by jeffchy 7 months ago
- 3 comments
#24 - run bash sample/t2v.sh,but why?
Issue -
State: closed - Opened by liwei0826 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#23 - Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device
Issue -
State: closed - Opened by GeLink9999 7 months ago
- 3 comments
#22 - some error to save output text to video
Issue -
State: closed - Opened by trongnk2106 7 months ago
- 9 comments
Labels: bug, automatic-stale, automatic-closing
#21 - please: one step take all 大神们,一步到位啊。
Issue -
State: closed - Opened by yuedajiong 7 months ago
- 4 comments
Labels: enhancement, automatic-stale, automatic-closing
#20 - Inference code
Issue -
State: closed - Opened by trongntt 7 months ago
- 2 comments
#19 - TypeError: PatchEmbed.__init__() got an unexpected keyword argument 'bias'
Issue -
State: closed - Opened by Xls1994 7 months ago
- 2 comments
#18 - sh sample/t2v.sh error,
Issue -
State: closed - Opened by ZerRui 7 months ago
- 3 comments
Labels: bug, automatic-stale, automatic-closing
#17 - Update README.md
Pull Request -
State: closed - Opened by eltociear 7 months ago
#16 - Does sora copy from this idea?
Issue -
State: closed - Opened by scorpioliu 7 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#15 - cannot import name 'CaptionProjection' from 'diffusers.models.embeddings'
Issue -
State: closed - Opened by Devin-Sun 7 months ago
- 1 comment
#14 - Some errors when running the LatteT2v
Issue -
State: closed - Opened by zgdjcls 7 months ago
- 17 comments
Labels: question, automatic-stale, automatic-closing
#13 - Asking for training code for t2v
Issue -
State: closed - Opened by Taldhi 7 months ago
- 2 comments
Labels: enhancement, automatic-stale, automatic-closing
#12 - Import error
Issue -
State: closed - Opened by Taldhi 7 months ago
- 5 comments
Labels: question, automatic-stale, automatic-closing
#11 - Difference between the training result of train.py and train_with_img.py?
Issue -
State: closed - Opened by SKBL5694 8 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#10 - preprocess dataset & t2v training
Issue -
State: closed - Opened by SKBL5694 8 months ago
- 5 comments
Labels: question, automatic-stale, automatic-closing
#9 - Question
Issue -
State: closed - Opened by ucasyjz 8 months ago
- 2 comments
Labels: bug, automatic-stale, automatic-closing
#7 - GPU Memory cost
Issue -
State: closed - Opened by SKBL5694 8 months ago
- 2 comments
Labels: question, automatic-stale, automatic-closing
#6 - FVD values of PVDM are strange
Issue -
State: closed - Opened by sihyun-yu 8 months ago
- 6 comments
Labels: question, automatic-stale, automatic-closing
#4 - Is there any bug in text2video generation mode?
Issue -
State: closed - Opened by howardgriffin 9 months ago
- 4 comments
#3 - Where is the paper?
Issue -
State: closed - Opened by howardgriffin 9 months ago
- 2 comments
#2 - What does 'args.extra' mean?
Issue -
State: closed - Opened by howardgriffin 9 months ago
- 1 comment
#1 - The provided pre-trained model is invalid
Issue -
State: closed - Opened by howardgriffin 9 months ago
- 1 comment