Vchitect Latte issues - Githubissues

Vchitect / Latte

Latte: Latent Diffusion Transformer for Video Generation.

Apache License 2.0

1.44k stars 147 forks source link

issues

Newest

Newest Most commented Recently updated Oldest Least commented Least recently updated

How can I turn on the autoregressive mode to generate >16 frame videos?

#42 luweiblues opened 4 months ago
1
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'

#41 counwakd opened 4 months ago
1
Update ucf101_image_datasets.py

#40 xszheng2020 closed 4 months ago
2
Training BatchSize

#39 ZekaiGalaxy opened 4 months ago
5
Issue about "LayerNormKernelImpl" not implemented for 'Half'

#38 kaiw7 closed 4 months ago
5
Can you provide the code for DDIM sampler

#37 lcwLcw123 closed 1 month ago
1
Re-implementation err on ffs experiment

#36 dummy702 opened 4 months ago
1
Preprocess of UCF101

#35 valencebond opened 4 months ago
14
Non-consecutive added token '<extra_id_99>' found.

#34 heatingma closed 4 months ago
2
torchrun --nnodes=1 --nproc_per_node=2 train_with_img.py --config ./configs/sky/sky_img_train.yaml error

#33 dpyneo opened 4 months ago
2
Discriminative tasks

#32 bhack opened 4 months ago
1
Cannot find model：LatteT2V.from_pretrained_2d

#31 bosima closed 4 months ago
1
What is

#30 olliacc opened 4 months ago
2
Does Latte support multiple GPUs

#29 afezeriaWrnbbmm closed 4 months ago
4
Latte的实时微信讨论组

#28 akebest opened 4 months ago
6
run bash sample/t2v.sh error

#27 afezeriaWrnbbmm closed 4 months ago
4
Excellent work, will there be an official support of images to vedio (like sora) ?

#26 jeffchy opened 4 months ago
4
T2V with >16 vedio_length output random noises

#25 jeffchy closed 4 months ago
3
run bash sample/t2v.sh,but why?

#24 liwei0826 opened 4 months ago
1
Pipelines loaded with `dtype=torch.float16` cannot run with `cpu` device

#23 GeLink9999 closed 4 months ago
3
some error to save output text to video

#22 trongnk2106 opened 4 months ago
8
please: one step take all 大神们，一步到位啊。

#21 yuedajiong opened 4 months ago
3
Inference code

#20 trongntt closed 4 months ago
2
TypeError: PatchEmbed.__init__() got an unexpected keyword argument 'bias'

#19 Xls1994 closed 4 months ago
2
sh sample/t2v.sh error,

#18 ZerRui opened 4 months ago
2
Update README.md

#17 eltociear closed 4 months ago
0
Does sora copy from this idea?

#16 scorpioliu opened 4 months ago
1
cannot import name 'CaptionProjection' from 'diffusers.models.embeddings'

#15 Devin-Sun closed 4 months ago
1
Some errors when running the LatteT2v

#14 zgdjcls opened 4 months ago
16
Asking for training code for t2v

#13 Taldhi opened 4 months ago
1
Import error

#12 Taldhi opened 4 months ago
4
Difference between the training result of train.py and train_with_img.py?

#11 SKBL5694 opened 5 months ago
1
preprocess dataset & t2v training

#10 SKBL5694 opened 5 months ago
4
Question

#9 yang326922943 opened 5 months ago
1
Bug

#8 yang326922943 closed 5 months ago
2
GPU Memory cost

#7 SKBL5694 opened 5 months ago
1
FVD values of PVDM are strange

#6 sihyun-yu opened 5 months ago
5
Bug

#5 yang326922943 closed 5 months ago
1
Is there any bug in text2video generation mode?

#4 howardgriffin closed 5 months ago
4
Where is the paper?

#3 howardgriffin closed 5 months ago
2
What does 'args.extra' mean?

#2 howardgriffin closed 6 months ago
1
The provided pre-trained model is invalid

#1 howardgriffin closed 6 months ago
1