Skip to content

Issues: baaivision/Emu3

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

45 Open 5 Closed
45 Open 5 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

why three special token is ignored in label
#53 opened Nov 27, 2024 by Pride-Huang
Could you provide the training scripts for Emu3-VisionTokenizer?
#52 opened Nov 21, 2024 by WilliamsToTo
demo运行错误
#51 opened Nov 20, 2024 by kangxiao18
1
是否支持Accelerate进行多卡推理
#50 opened Nov 15, 2024 by heavenhellchen
about EMU3-CHAT on the MME benchmark score
#49 opened Nov 14, 2024 by muxizju
Can't load visual processor
#48 opened Nov 11, 2024 by OliviaWang123456
1
Can you give some of your pretraing dataset
#46 opened Nov 6, 2024 by ZHUI
Query about data preparation and token
#45 opened Nov 1, 2024 by URRealHero
How to generate video using the model you released, can you provide an inference scripts?
#44 opened Oct 31, 2024 by xinsir6
1
运行multimodal_understanding.py遇到闪退，未抛出错误
#42 opened Oct 29, 2024 by BrooksXiaoxi
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 opened Oct 28, 2024 by xianshenglan123
这个适配的Python版本是那个
#40 opened Oct 27, 2024 by xianshenglan123
2
Issues with flash_attn
#39 opened Oct 27, 2024 by ohjasd098
1
How to generate videos?
#38 opened Oct 24, 2024 by ShootingWong
4
运行multimodal_understanding.py报错，只改了模型从魔搭社区下载那一部分
#36 opened Oct 24, 2024 by zhrli
11
multi images input or multi images generation?
#35 opened Oct 23, 2024 by FanqingM
1
JSON format in pre-training stage for Emu3
#34 opened Oct 22, 2024 by leofan90
video 视觉理解
#33 opened Oct 22, 2024 by Cherryjingyao
Training scripts of ti2t
#32 opened Oct 22, 2024 by yimuu
运行第一个Demo的时候报错了
#31 opened Oct 21, 2024 by 3244we
4
only use 1d rope?
#30 opened Oct 21, 2024 by junwuzhang19
1
Details Regarding Post-Training
#29 opened Oct 21, 2024 by Doctor-James
Can we use the released EMU3-Gen (image model) to do video generation?
#27 opened Oct 15, 2024 by sbyebss
Question on the vocabulary size
#26 opened Oct 15, 2024 by PPPPPsanG
1
The article mentioned that 1M of image and text pairs were annotated using gpt4v. How can I obtain this data?
#25 opened Oct 12, 2024 by zhangqingwu
ProTip! no:milestone will show everything without a milestone.