issues
search
baaivision
/
Emu3
Next-Token Prediction is All You Need
Apache License 2.0
1.81k
stars
71
forks
source link
issues
Newest
Newest
Most commented
Recently updated
Oldest
Least commented
Least recently updated
是否支持Accelerate进行多卡推理
#50
heavenhellchen
opened
15 hours ago
0
about EMU3-CHAT on the MME benchmark score
#49
muxizju
opened
1 day ago
0
Can't load visual processor
#48
OliviaWang123456
opened
4 days ago
1
any scripts or instruction how to obtain MSCOCO-30k evaluation score?
#47
blueardour
closed
4 days ago
0
Can you give some of your pretraing dataset
#46
ZHUI
opened
1 week ago
0
Query about data preparation and token
#45
URRealHero
opened
2 weeks ago
0
How to generate video using the model you released, can you provide an inference scripts?
#44
xinsir6
opened
2 weeks ago
0
ValueError: Regex error: Compiled regex exceeds size limit of 10485760 bytes
#43
RavenKiller
closed
1 day ago
0
运行multimodal_understanding.py遇到闪退，未抛出错误
#42
BrooksXiaoxi
opened
2 weeks ago
0
你好 我将model下载到本地运行是提示 libcudnn.so.8: cannot open shared object file: No such file or directory
#41
xianshenglan123
opened
2 weeks ago
0
这个适配的Python版本是那个
#40
xianshenglan123
opened
2 weeks ago
2
Issues with flash_attn
#39
ohjasd098
opened
2 weeks ago
1
How to generate videos?
#38
ShootingWong
opened
3 weeks ago
4
Use 🤗Transformers to run Emu3-Chat/Stage1 for vision-language understanding的示例代码中pos_inputs未定义
#37
qingchen177
closed
3 weeks ago
1
运行multimodal_understanding.py报错，只改了模型从魔搭社区下载那一部分
#36
zhrli
opened
3 weeks ago
11
multi images input or multi images generation?
#35
FanqingM
opened
3 weeks ago
1
JSON format in pre-training stage for Emu3
#34
leofan90
opened
3 weeks ago
0
video 视觉理解
#33
Cherryjingyao
opened
3 weeks ago
0
Training scripts of ti2t
#32
yimuu
opened
3 weeks ago
0
运行第一个Demo的时候报错了
#31
3244we
opened
3 weeks ago
4
only use 1d rope?
#30
junwuzhang19
opened
3 weeks ago
1
Details Regarding Post-Training
#29
Doctor-James
opened
3 weeks ago
0
Update Replicate Link
#28
chenxwh
opened
4 weeks ago
0
Can we use the released EMU3-Gen (image model) to do video generation?
#27
sbyebss
opened
1 month ago
0
Question on the vocabulary size
#26
PPPPPsanG
opened
1 month ago
1
The article mentioned that 1M of image and text pairs were annotated using gpt4v. How can I obtain this data?
#25
zhangqingwu
opened
1 month ago
0
The scale of image understanding training data
#24
SxJyJay
opened
1 month ago
0
How to control image resolution for Emu3-Gen?
#23
YunjieYu
opened
1 month ago
1
Video Model Weights Release
#22
zpx01
opened
1 month ago
0
"flash_attn" were not found in your environment
#21
czhhzc
opened
1 month ago
2
cannot inference on A100 40GB
#20
quang-ngh
opened
1 month ago
2
No QK Norm? How it compares to Chameleon?
#19
DEBIHOOD
opened
1 month ago
1
how long it takes to generate an image
#18
zc1023
opened
1 month ago
4
training script release?
#17
Njasa2k
opened
1 month ago
1
About post processing
#16
junwuzhang19
opened
1 month ago
2
readme image cannot be read easily with dark mode on
#15
kasumi-1
closed
1 month ago
1
模型太大了, 能否提供更小的版本?
#14
win10ogod
opened
1 month ago
9
chore: update image_processing_emu3visionvq.py
#13
eltociear
opened
1 month ago
0
About separation models & image to video
#12
AA-Developer
opened
1 month ago
1
Add Replicate demo and API
#11
chenxwh
closed
1 month ago
0
Generation inference with interleaved input
#10
ys-zong
opened
1 month ago
2
How is the COT performance? Have you tested on the benchmark like M3COT?
#9
FanqingM
opened
1 month ago
1
Add information about training
#7
Andrey36652
opened
1 month ago
3
Video Tokenizer Inference
#6
Epiphqny
opened
1 month ago
4
Torch should be above flash-attn in requirements.txt
#5
jpgallegoar
opened
1 month ago
1
Is 'tiktokn' in requirements.txt meant to be 'tiktoken'?
#4
WingLoong233
opened
1 month ago
1
Video Generation Model
#3
jacklishufan
opened
1 month ago
1
Seperate weights for understanding and generation
#2
QuLiao1117
opened
1 month ago
1
What is the difference between Emu3-Chat and Emu3-Gen?
#1
charlesCXK
opened
1 month ago
1