Ecosyste.ms: Timeline
Browse the timeline of events for every public repo on GitHub. Data updated hourly from GH Archive.
zRzRzRzRzRzRzR closed an issue on THUDM/CogVideo
cogvideox微调的代码选择
@zRzRzRzRzRzRzR @wenyihong @OleehyO @huangshiyu13 @bertjiazheng 开发者您好，感谢cogvideo的开源工作。有2个问题微调方面的问题想请教一下： 1.CogVideoX-5B，CogVideoX-5B-I2V，这2个项目项目可以用cogvideox-factory项目微调吗（代码地址：https://github...
zRzRzRzRzRzRzR closed an issue on THUDM/CogVideo
star完钱在哪里领
### System Info / 系統信息 无 ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [X] My own modified scripts / 我自己修改的脚本和任务 ### Reproduction / 复现过程 无 ### Expected behavior / 期待表现...
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogVideo
请问这是哪里的截图？我们从未允许这样的事情。这是一个严重的事件。 如果是智谱员工做的，请通过我们邮件 [email protected] 举报。 感谢支持。
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogAgent
可以，我们后续会做迁移，模型开发时间比较赶，还是使用的4.44.2的格式在做的，我们之后会考虑迁移到4.47.0版本
zRzRzRzRzRzRzR pushed 23 commits to main zRzRzRzRzRzRzR/LiveBench
- Update README.md add note for Windows users 0870422
- update model_adapter.py 37b5027
- update figure 174d07c
- Add line separator b87e779
- add --livebench-release-option to all runner files 4de3327
- update api model lists 7104134
- handle edge case in math olympiad judging ee0b887
- handle edge case in tablejoin judging f774d19
- add debugging option for AMPS_Hard, math_comp, and web_of_lies_v2 e84e548
- bump version 0678e4e
- fix bug in download_leaderboard 3953c6c
- Merge pull request #48 from codepharmer/patch-1 Update README.md f050f8c
- Update README.md 85cae69
- Merge remote-tracking branch 'upstream/main' 1c779c2
- add changelog fb1380a
- update changelog 1f37ca3
- Update changelog.md a0fc4fe
- Update README.md a58e552
- update readme 8edea2b
- Merge pull request #68 from dylanjcastillo/main Add line separator 3055d6a
- and 3 more ...
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogAgent
单次推理中没有进行反思，而是根据用户的输入（或者用脚本实现输入）后作出下一步规划
zRzRzRzRzRzRzR pushed 2 commits to main THUDM/CogAgent
zRzRzRzRzRzRzR closed a pull request on THUDM/CogAgent
fix windows run error
windows系统运行报错: Windows-11-10.0.22631-SP0 operating system is not currently supported! ! 改为不区分大小写 win正常运行
zRzRzRzRzRzRzR closed an issue on THUDM/CogAgent
send message
https://github.com/user-attachments/assets/4d39fe6a-d460-427c-a930-b7cbe0d082f5
zRzRzRzRzRzRzR closed an issue on THUDM/CogAgent
send email
https://github.com/user-attachments/assets/87f00f97-1c4f-4152-b7c0-d145742cb910
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogVideo
1.5版本在发布第一个版本可能配置没有正确，但是模型权重是正确的，确保使用diffusers最新的依赖和最新的HF模型仓库来进行使用。
zRzRzRzRzRzRzR closed an issue on THUDM/CogVideo
V1.5版本生成视频闪烁
### System Info / 系統信息 None ### Information / 问题信息 - [x] The official example scripts / 官方的示例脚本 - [ ] My own modified scripts / 我自己修改的脚本和任务 ### Reproduction / 复现过程 https://github.com/user-at...
zRzRzRzRzRzRzR closed an issue on THUDM/CogVideo
Support Multi-User for Gradio Web Demo
### Feature request / 功能建议 how to support multiple user for same gradio web instance ? ### Motivation / 动机 1 model instance to serve many users generation at the same time ### Your contributio...
zRzRzRzRzRzRzR closed an issue on THUDM/CogVideo
How to finetune CogVideoX-2B on multiple nodes?
### System Info / 系統信息 cuda=12.1 python=3.10.14 diffusers=0.31.0.dev ### Information / 问题信息 - [X] The official example scripts / 官方的示例脚本 - [ ] My own modified scripts / 我自己修改的脚本和任务 ### Re...
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogVideo
> 尝试低分辨率微调模型后 想知道这个地方是用什么方法微调，用了哪个脚本呢
zRzRzRzRzRzRzR created a comment on an issue on THUDM/CogVideo
关于你提到啊的这个问题，首先，你提到的这个分辨率并不在支持的分辨率内 <img width="156" alt="image" src="https://github.com/user-attachments/assets/017dbbee-2774-4947-8bb2-b605a378be95" /> 如果你将分辨率调整为1024 * 768 有解决问题，很有可能是在模型不支持的分辨率...
zRzRzRzRzRzRzR pushed 66 commits to main zRzRzRzRzRzRzR/diffusers
- Fix Mochi Quality Issues (#10033) * update * update * update * update * update * update * update ... 128b96f
- [tests] Remove/rename unsupported quantization torchao type (#10263) update 1524781
- [docs] delete_adapters() (#10245) delete_adapters Co-authored-by: Sayak Paul <[email protected]> 2739241
- [Community Pipeline] Fix typo that cause error on regional prompting pipeline (#10251) fix: fix typo that cause error 9c68c94
- Add `set_shift` to FlowMatchEulerDiscreteScheduler (#10269) ec1c7a7
- [LoRA] feat: lora support for SANA. (#10234) * feat: lora support for SANA. * make fix-copies * rename test cl... 9408aa2
- [chore] fix: licensing headers in mochi and ltx (#10275) fix: licensing header. ba6fd6e
- Use `torch` in `get_2d_rotary_pos_embed` (#10155) * Use `torch` in `get_2d_rotary_pos_embed` * Add deprecation 0ac52d6
- [chore] fix: reamde -> readme (#10276) fix: reamde -> readme 63cdf9c
- Make `time_embed_dim` of `UNet2DModel` changeable (#10262) 88b015d
- Support pass kwargs to sd3 custom attention processor (#9818) * Support pass kwargs to sd3 custom attention processo... 8eb73c8
- Flux Control(Depth/Canny) + Inpaint (#10192) * flux_control_inpaint - failing test_flux_different_prompts * remov... 83709d5
- Fix sigma_last with use_flow_sigmas (#10267) e222246
- Fix Doc links in GGUF and Quantization overview docs (#10279) * update * Update docs/source/en/quantization/gguf.m... b389f33
- Make zeroing prompt embeds for Mochi Pipeline configurable (#10284) update 8304adc
- [Single File] Add single file support for Flux Canny, Depth and Fill (#10288) update 862a7d5
- [tests] Fix broken cuda, nightly and lora tests on main for CogVideoX (#10270) fix joint pos embedding device c4c99c3
- Rename Mochi integration test correctly (#10220) rename integration test f66bd32
- [tests] remove nullop import checks from lora tests (#10273) remove nullop imports f35a387
- [chore] Update README_sana.md to update the default model (#10285) Update README_sana.md to update the default model 9c0e20d
- and 46 more ...