Issues
- 0
- 0
- 7
Which Python version are you supporting?
#84 opened by zerothi - 3
The in-context learning sample for pretrained model does not work as expected.
#45 opened by ShunsukeOnoo - 0
Using a mask with image inpainting
#83 opened by Woodyet - 0
Can you share your cleaned WebVid annotation?
#82 opened by dreamerlin - 2
how to funetunning on custom dataset?
#78 opened by dragen1860 - 0
- 1
Generate from any prompt sequence
#79 opened by lzw-lzw - 0
- 3
- 17
显存大小不一致
#71 opened by SANJINGSHOU14 - 1
Is there a performance gap between causal cformer and a bi-directional one just like Q-former?
#37 opened by DietDietDiet - 2
Emu models weights is not downloading
#76 opened by ashutoshbk - 7
Too Many Request when Downloading YT-SB-1b
#72 opened by LengSicong - 0
Hu is whu, humm?
#42 opened by lootnath - 1
Eval Dataset
#41 opened by jybxie123 - 2
- 1
Issue with EMU2-Gen
#75 opened by Woodyet - 1
Inquiry Regarding the Integration of Domain-Specific Knowledge into Emu2 for Enhanced Multimodal Learning
#57 opened by yihong1120 - 5
大佬你好,请问可以提供下本地部署gradio界面的代码吗?
#73 opened by zhangdanfeng888 - 0
如何进行finetune?
#74 opened by jyC23333 - 3
- 1
How to evaluate REC tasks
#66 opened by theFool32 - 1
能不能结合 emu2-chat 和 emu2-gen
#69 opened by prefixRAINSTARsuffix - 0
Will the training code be released ?
#70 opened by prefixRAINSTARsuffix - 2
Invitation to support EMU2 in VLMEvalKit
#64 opened by kennymckormick - 3
Emu2-Gen 所需的显存是多少啊
#67 opened by DaBaiTuu - 1
- 1
There seems to be some discrepancy between the cogvlm indicators posted in the paper.
#65 opened by xmy0916 - 2
How to train few-shot ability?
#60 opened by jyC23333 - 2
啊这。。。。
#58 opened by Arcmoon-Hu - 11
How to use video as Emu2-chat's input?
#63 opened by SANJINGSHOU14 - 11
本地部署效果与huggingface的demo效果差异巨大
#59 opened by lucifer443 - 2
How to run Emu2-gen with native pytorch?
#61 opened by cliangyu - 3
RuntimeError: shape mismatch
#62 opened by timwalls - 6
Weight files take up too much disk space
#47 opened by VladAndronik - 2
offline infer different from your demo.
#54 opened by xmy0916 - 5
- 1
question about the visual autoencoder
#55 opened by Junction4Nako - 1
- 3
Generate video from any prompt sequence
#46 opened by zhw-zhang - 4
emu2-gen A100 OOM
#52 opened by chuxing - 8
The n_query and v_query in EMU2
#50 opened by Arsiuuu - 0
does plan to update llama to llama2?
#43 opened by verigle - 2
Question about training
#35 opened by HongyanZhi - 0
Image generation evaluation
#40 opened by Ber666 - 1
How to inference dialogue with EMU?
#38 opened by JeavanCode - 1
how to get the label data which is needed in video_webdataset_maker_YT1b_sb.py
#39 opened by LightningApple - 0