Ecosyste.ms: Issues
An open API service for providing issue and pull request metadata for open source projects.
GitHub / baaivision/Emu issues and pull requests
#93 - Does any emu2 series model support interleaved text and images generation?
Issue -
State: open - Opened by URRealHero 2 months ago
#92 - 可以问一下是否有机会release train的代码吗?感谢
Issue -
State: open - Opened by icemoon-creative 4 months ago
#91 - When will Emu 3 be released?
Issue -
State: open - Opened by mutonix 5 months ago
- 1 comment
#90 - Will the pre-training code be released in the future?
Issue -
State: open - Opened by handsomelys 5 months ago
- 1 comment
#89 - Wrong outputs
Issue -
State: open - Opened by czhhzc 8 months ago
- 1 comment
#88 - Environment installation failed
Issue -
State: closed - Opened by sugary199 8 months ago
- 2 comments
#87 - License confusion
Issue -
State: open - Opened by NuiMrme 8 months ago
- 1 comment
#86 - Will the "CapsFusion-grounded-100M" dataset be public available?
Issue -
State: closed - Opened by ziyye 8 months ago
#85 - 多机推理时卡住
Issue -
State: closed - Opened by rexain 8 months ago
#84 - Which Python version are you supporting?
Issue -
State: open - Opened by zerothi 8 months ago
- 7 comments
#83 - Using a mask with image inpainting
Issue -
State: closed - Opened by Woodyet 9 months ago
- 2 comments
#82 - Can you share your cleaned WebVid annotation?
Issue -
State: open - Opened by dreamerlin 10 months ago
#81 - any advice on finetunning on A800 80GB GPU machines?
Issue -
State: open - Opened by dragen1860 10 months ago
#80 - Details on in-context example selection/construction
Issue -
State: open - Opened by sachit-menon 10 months ago
#79 - Generate from any prompt sequence
Issue -
State: closed - Opened by lzw-lzw 10 months ago
- 1 comment
#78 - how to funetunning on custom dataset?
Issue -
State: open - Opened by dragen1860 10 months ago
- 2 comments
#77 - Redundant outputs when performing in-context learning
Issue -
State: open - Opened by chan-ming 10 months ago
- 3 comments
#76 - Emu models weights is not downloading
Issue -
State: open - Opened by ashutoshbk 10 months ago
- 2 comments
#75 - Issue with EMU2-Gen
Issue -
State: closed - Opened by Woodyet 10 months ago
- 1 comment
#74 - 如何进行finetune?
Issue -
State: open - Opened by jyC23333 10 months ago
#73 - 大佬你好,请问可以提供下本地部署gradio界面的代码吗?
Issue -
State: open - Opened by zhangdanfeng888 10 months ago
- 5 comments
#72 - Too Many Request when Downloading YT-SB-1b
Issue -
State: open - Opened by LengSicong 10 months ago
- 7 comments
#71 - 显存大小不一致
Issue -
State: closed - Opened by chaochen1998 10 months ago
- 17 comments
#70 - Will the training code be released ?
Issue -
State: open - Opened by prefixRAINSTARsuffix 10 months ago
#69 - 能不能结合 emu2-chat 和 emu2-gen
Issue -
State: closed - Opened by prefixRAINSTARsuffix 10 months ago
- 2 comments
#68 - 内存要求
Issue -
State: open - Opened by CHY-coder 10 months ago
- 1 comment
#67 - Emu2-Gen 所需的显存是多少啊
Issue -
State: closed - Opened by DaBaiTuu 11 months ago
- 3 comments
#66 - How to evaluate REC tasks
Issue -
State: closed - Opened by theFool32 11 months ago
- 1 comment
#65 - There seems to be some discrepancy between the cogvlm indicators posted in the paper.
Issue -
State: open - Opened by xmy0916 11 months ago
- 1 comment
#64 - Invitation to support EMU2 in VLMEvalKit
Issue -
State: open - Opened by kennymckormick 11 months ago
- 2 comments
#63 - How to use video as Emu2-chat's input?
Issue -
State: closed - Opened by chaochen1998 11 months ago
- 11 comments
#62 - RuntimeError: shape mismatch
Issue -
State: closed - Opened by timwalls 11 months ago
- 3 comments
#61 - How to run Emu2-gen with native pytorch?
Issue -
State: closed - Opened by cliangyu 11 months ago
- 2 comments
#60 - How to train few-shot ability?
Issue -
State: closed - Opened by jyC23333 11 months ago
- 2 comments
#59 - 本地部署效果与huggingface的demo效果差异巨大
Issue -
State: closed - Opened by lucifer443 11 months ago
- 11 comments
#58 - 啊这。。。。
Issue -
State: closed - Opened by Arcmoon-Hu 11 months ago
- 2 comments
#57 - Inquiry Regarding the Integration of Domain-Specific Knowledge into Emu2 for Enhanced Multimodal Learning
Issue -
State: open - Opened by yihong1120 11 months ago
- 1 comment
#56 - Question about text classification loss and image regression loss
Issue -
State: closed - Opened by xmy0916 11 months ago
- 5 comments
#55 - question about the visual autoencoder
Issue -
State: open - Opened by Junction4Nako 11 months ago
- 1 comment
#54 - offline infer different from your demo.
Issue -
State: closed - Opened by xmy0916 11 months ago
- 2 comments
#53 - Is there any plan to replace the language model with a smaller one?
Issue -
State: closed - Opened by xmy0916 11 months ago
- 1 comment
#52 - emu2-gen A100 OOM
Issue -
State: closed - Opened by chuxing 11 months ago
- 4 comments
#51 - upload pytorch native models and add demo codes
Pull Request -
State: closed - Opened by ryanzhangfan 11 months ago
#50 - The n_query and v_query in EMU2
Issue -
State: closed - Opened by Arsiuuu 11 months ago
- 8 comments
#49 - 何时支持中文?
Issue -
State: closed - Opened by zky001 11 months ago
- 3 comments
#48 - Update README.md
Pull Request -
State: closed - Opened by zhangxiaosong18 11 months ago
#47 - Weight files take up too much disk space
Issue -
State: closed - Opened by VladAndronik 11 months ago
- 6 comments
#46 - Generate video from any prompt sequence
Issue -
State: open - Opened by zhw-zhang 11 months ago
- 4 comments
#45 - The in-context learning sample for pretrained model does not work as expected.
Issue -
State: open - Opened by ShunsukeOnoo 12 months ago
- 3 comments
#44 - [Question] Implementation details of image regression loss
Issue -
State: open - Opened by liuheng0111 12 months ago
- 2 comments
#43 - does plan to update llama to llama2?
Issue -
State: open - Opened by verigle 12 months ago
- 1 comment
#41 - Eval Dataset
Issue -
State: closed - Opened by jybxie123 about 1 year ago
- 1 comment
#40 - Image generation evaluation
Issue -
State: open - Opened by Ber666 about 1 year ago
#39 - how to get the label data which is needed in video_webdataset_maker_YT1b_sb.py
Issue -
State: open - Opened by LightningApple about 1 year ago
- 1 comment
#39 - how to get the label data which is needed in video_webdataset_maker_YT1b_sb.py
Issue -
State: open - Opened by LightningApple about 1 year ago
- 1 comment
#38 - How to inference dialogue with EMU?
Issue -
State: open - Opened by JeavanCode about 1 year ago
- 1 comment
#37 - Is there a performance gap between causal cformer and a bi-directional one just like Q-former?
Issue -
State: open - Opened by DietDietDiet about 1 year ago
- 1 comment
#36 - What's the difference between Emu_pretain.pt and pytorch_model.bin?
Issue -
State: open - Opened by likanchuan about 1 year ago
#36 - What's the difference between Emu_pretain.pt and pytorch_model.bin?
Issue -
State: open - Opened by likanchuan about 1 year ago
#35 - Question about training
Issue -
State: open - Opened by HongyanZhi about 1 year ago
- 2 comments
#34 - Batch inference.
Issue -
State: closed - Opened by talha1503 about 1 year ago
- 1 comment
#33 - Cannot reproduce image2text score on coco dataset (CIDEr)
Issue -
State: open - Opened by byeongGuks about 1 year ago
- 3 comments
#32 - feat: add yt-sb-1b dataset
Pull Request -
State: closed - Opened by SlotherCui about 1 year ago
#32 - feat: add yt-sb-1b dataset
Pull Request -
State: closed - Opened by SlotherCui about 1 year ago
#31 - Error running `image_inference.py`
Issue -
State: closed - Opened by Ber666 about 1 year ago
- 2 comments
#31 - Error running `image_inference.py`
Issue -
State: closed - Opened by Ber666 about 1 year ago
- 2 comments
#30 - Cannot reproduce the results on VisDial
Issue -
State: closed - Opened by stdKonjac about 1 year ago
- 1 comment
#29 - What is the rationale to name the paper Emu?
Issue -
State: closed - Opened by patrick-llgc about 1 year ago
- 1 comment
#28 - Any plan to make the data and pretrain code publicable?
Issue -
State: open - Opened by yotofu about 1 year ago
#27 - splitting the checkpoint into several smaller files
Issue -
State: open - Opened by yellow-binary-tree about 1 year ago
#27 - splitting the checkpoint into several smaller files
Issue -
State: open - Opened by yellow-binary-tree about 1 year ago
#26 - Is there any smaller variants?
Issue -
State: closed - Opened by YifanXu74 about 1 year ago
- 2 comments
#25 - Plan of releasing YT-Storyboard-1B Dataset
Issue -
State: closed - Opened by sijeh about 1 year ago
- 1 comment
#24 - Inquire on the evaluation code
Issue -
State: closed - Opened by HenryHZY about 1 year ago
- 2 comments
#23 - Online demo vs. inference example result different.
Issue -
State: closed - Opened by DaFuCoding over 1 year ago
- 2 comments
#23 - Online demo vs. inference example result different.
Issue -
State: closed - Opened by DaFuCoding over 1 year ago
- 2 comments
#22 - Implementation in generate_image()
Issue -
State: open - Opened by jwh97nn over 1 year ago
- 1 comment
#22 - Implementation in generate_image()
Issue -
State: open - Opened by jwh97nn over 1 year ago
- 1 comment
#21 - Will you share the training loss log?
Issue -
State: open - Opened by bsxxdw over 1 year ago
#21 - Will you share the training loss log?
Issue -
State: open - Opened by bsxxdw over 1 year ago
#20 - add multimodal image generation codes and examples
Pull Request -
State: closed - Opened by ryanzhangfan over 1 year ago
#20 - add multimodal image generation codes and examples
Pull Request -
State: closed - Opened by ryanzhangfan over 1 year ago
#19 - LLama的license问题
Issue -
State: closed - Opened by lj163ucas over 1 year ago
- 1 comment
#19 - LLama的license问题
Issue -
State: closed - Opened by lj163ucas over 1 year ago
- 1 comment
#18 - Image Generation
Issue -
State: closed - Opened by jshilong over 1 year ago
- 2 comments
#18 - Image Generation
Issue -
State: closed - Opened by jshilong over 1 year ago
- 2 comments
#17 - Time for releasing the pre-training code
Issue -
State: open - Opened by mutonix over 1 year ago
#17 - Time for releasing the pre-training code
Issue -
State: open - Opened by mutonix over 1 year ago
#16 - Question about training objectives
Issue -
State: closed - Opened by jwh97nn over 1 year ago
- 2 comments
#16 - Question about training objectives
Issue -
State: closed - Opened by jwh97nn over 1 year ago
- 2 comments
#15 - Multi-GPU support
Issue -
State: open - Opened by ifsheldon over 1 year ago
#15 - Multi-GPU support
Issue -
State: open - Opened by ifsheldon over 1 year ago
#14 - tools for processing YT-Storyboad-1B
Issue -
State: closed - Opened by distillation-dcf over 1 year ago
- 1 comment
#13 - question about the pretrained weights for image encoder EVA-clip
Issue -
State: closed - Opened by Lechatelia over 1 year ago
- 1 comment
#12 - add dependency
Pull Request -
State: closed - Opened by ifsheldon over 1 year ago
#12 - add dependency
Pull Request -
State: closed - Opened by ifsheldon over 1 year ago
#11 - add how to run gradio demo locally
Issue -
State: open - Opened by AK391 over 1 year ago
#11 - add how to run gradio demo locally
Issue -
State: open - Opened by AK391 over 1 year ago
#10 - Inference with video
Issue -
State: closed - Opened by shahkalp09 over 1 year ago
- 2 comments
#10 - Inference with video
Issue -
State: closed - Opened by shahkalp09 over 1 year ago
- 2 comments