issues
search
Vchitect
/
Latte
Latte: Latent Diffusion Transformer for Video Generation.
Apache License 2.0
1.45k
stars
147
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
what the param <input_sq_size> stands for?
#92
leonardodora
closed
2 weeks ago
2
Batch Size Ablations
#91
fan23j
closed
1 week ago
1
Can Latte train for I2V tasks?
#90
0Godness
opened
1 month ago
2
Update environment.yml
#89
Upper9527
closed
1 month ago
0
Update pipeline_videogen.py
#88
Upper9527
closed
1 month ago
0
Update train.py
#87
Upper9527
closed
1 month ago
0
Update latte.py
#86
Upper9527
closed
1 month ago
0
Update environment.yml
#85
Upper9527
closed
1 month ago
0
模型在ucf101上无法收敛
#84
renyuanzhe
opened
1 month ago
5
Any plan to implement Latte in HuggingFace's diffusers library?
#83
Quest4AiJ
opened
1 month ago
1
How to get preprocessed_ffs
#82
zhang-haojie
opened
1 month ago
2
Error once speed up training
#81
moeinheidari7829
opened
1 month ago
2
Question: evaluate the FVD
#80
Alienge
closed
1 month ago
6
the code of variant 4
#79
pangpangjy
opened
1 month ago
1
how to place and preprocess these datasets
#78
renyuanzhe
opened
2 months ago
6
Question: model code and design choices
#77
mrartemevmorphic
opened
2 months ago
1
视频帧率
#76
fenghe12
opened
2 months ago
1
question on t2v model training
#75
diffusion-lover
opened
2 months ago
1
有关时长的问题。
#74
LinQianhe02grey
opened
2 months ago
3
About video VAE
#73
Darius-H
opened
2 months ago
1
Questions about the *0.18215 and /0.18215 operation
#72
haibao-yu
closed
2 months ago
2
Is autoregression possible?
#71
zhaohm14
opened
2 months ago
3
No positional embeddings in LatteT2V?
#70
DanielSHKao
closed
2 months ago
0
fix xformer input shape of Q,K,V in latte.py
#69
tianyma
closed
2 months ago
1
[Feature] WIP: support sequence parallel
#68
HIT-cwh
opened
3 months ago
0
FaceForensics数据集
#67
likeatingcake
opened
3 months ago
2
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:
#66
likeatingcake
opened
3 months ago
2
Evaluate the FVD?
#65
huangjch526
closed
2 months ago
5
CUDA out of memory
#64
likeatingcake
opened
3 months ago
4
Fix typo
#63
AlonzoLeeeooo
closed
3 months ago
0
image_size = [256,512]
#62
likeatingcake
opened
3 months ago
4
RuntimeError: "slow_conv2d_cpu" not implemented for 'Half'
#61
likeatingcake
closed
3 months ago
2
RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'
#60
likeatingcake
opened
3 months ago
1
What is the difference between Latte and ViViT?
#59
Leeeshuz
opened
3 months ago
2
trained and sample result very strange (我自己训练复现的效果很奇怪)
#58
huangjch526
closed
3 months ago
21
Why choose these datasets and why not compare with pika, SVD or Gen2?
#57
qiuhaining
opened
3 months ago
1
Extra key in ucf101.pt
#56
wang-muhan
opened
3 months ago
7
About resume checkpoint
#55
kaiw7
opened
4 months ago
2
About Training Speed
#54
ZekaiGalaxy
opened
4 months ago
5
diffusion noise modify
#53
ErwinKC
opened
4 months ago
1
Implementation of compression frame patch embedding (Fig. 3b)
#52
paulchhuang
closed
4 months ago
2
Option to use ReBased Linear Attention and RingAttention
#51
kabachuha
opened
4 months ago
3
t2v只支持16帧吗?我改成更多比如32帧就啥都看不到了
#50
epcsoft
opened
4 months ago
1
如何复现主页展示的t2v效果?
#49
HRain1016
opened
4 months ago
3
Train code of t2v?
#48
kings-rgb
opened
4 months ago
6
About evaluation
#47
kaiw7
opened
4 months ago
3
t2i代码疑问
#46
LiuhanChen-github
opened
4 months ago
1
anyone meet zero grad?零梯度?
#45
huangjch526
closed
3 months ago
1
Code Reuse
#44
LinB203
opened
4 months ago
5
how to get 2048 videos for computing FVD?
#43
hdjsjyl
opened
4 months ago
3
Next