Ecosyste.ms: Issues

An open API service for providing issue and pull request metadata for open source projects.

GitHub / THUDM/CogVideo issues and pull requests

#323 - Question about learnable position embedding in I2V model

Issue - State: closed - Opened by xvjiarui about 2 months ago - 3 comments

#322 - Support for ControlNet

Issue - State: open - Opened by tliby about 2 months ago - 2 comments

#321 - Discord invite link has expired

Issue - State: closed - Opened by ameasure about 2 months ago - 1 comment

#320 - Load LoRA for diffusers test

Issue - State: closed - Opened by wenqsun about 2 months ago - 2 comments

#319 - Can cogvlm2-llama3-caption generate Chinese caption?

Issue - State: closed - Opened by MinliangLin about 2 months ago - 1 comment

#318 - Friendly links fine-tuning mode KoolCogVideo

Pull Request - State: closed - Opened by glide-the about 2 months ago

#316 - Slow loading of model and very delay in image to video

Issue - State: open - Opened by Neethan54 about 2 months ago - 22 comments

#310 - Why is Maximum Prompt Length 226?

Issue - State: closed - Opened by Yuancheng-Xu about 2 months ago - 4 comments

#309 - CogVideoX-2B SFT diffuser

Issue - State: closed - Opened by HaoZhang990127 about 2 months ago - 4 comments

#306 - CogVideoX-5B-I2V diffusers finetune support

Issue - State: closed - Opened by JonathanLi19 about 2 months ago - 2 comments

#300 - Image to video ending frame option

Issue - State: closed - Opened by rodjjo about 2 months ago - 2 comments

#294 - CogVideo是可以使用图片训练的，请问如何使用图片进行训练

Issue - State: closed - Opened by schhaohao about 2 months ago - 5 comments

#293 - THUDM/CogVideoX-5b-I2V not found

Issue - State: closed - Opened by SoftologyPro about 2 months ago - 3 comments

#291 - I2V model PT seems corrupt

Issue - State: closed - Opened by phr00t about 2 months ago - 10 comments

#277 - new finetune code report error

Issue - State: closed - Opened by zyssyz123 2 months ago - 5 comments

#276 - Help SAT model convert to diffuser model

Issue - State: closed - Opened by KihongK 2 months ago - 5 comments

#266 - How to support a new resolution?

Issue - State: closed - Opened by trouble-maker007 2 months ago - 1 comment

#256 - 5B model finetune multi gpu, cuda out of memory

Issue - State: closed - Opened by zyssyz123 2 months ago - 3 comments

#247 - do you guys have a plan about 10B model

Issue - State: closed - Opened by codeplay0000 2 months ago - 5 comments

#245 - cli_demo_quantization.py does not work with latest torchao (git)

Issue - State: closed - Opened by backface 2 months ago - 1 comment

#235 - Ask about learning rate schedule

Issue - State: open - Opened by yjhong89 2 months ago - 2 comments

#231 - Compute resources used to train CogVideoX

Issue - State: closed - Opened by michal-stary 2 months ago - 3 comments

#225 - Fully fine-tune config for CogiVideo-5B model

Issue - State: closed - Opened by xvjiarui 2 months ago - 12 comments

#222 - MAC下运行报错

Issue - State: open - Opened by taozhiyuai 2 months ago - 19 comments

#211 - Details of finetuning an Image-to-Video model

Issue - State: closed - Opened by tedfeng424 3 months ago - 5 comments
Labels: good first issue

#204 - Running CogVideoX-5B on T4/V100 Free Colab Space

Issue - State: closed - Opened by ProKSMT 3 months ago - 25 comments
Labels: enhancement, good first issue, help wanted

#202 - GPU usage can not always 100%

Issue - State: closed - Opened by GFENGG 3 months ago - 4 comments

#194 - Work plan and enhancement / 工作计划和用户诉求

Issue - State: open - Opened by zRzRzRzRzRzRzR 3 months ago - 18 comments
Labels: enhancement

#186 - Will you release the training code of VAE.

Issue - State: closed - Opened by serend1p1ty 3 months ago - 3 comments

#177 - KeyError: 'shadow'

Issue - State: closed - Opened by SpringtoString 3 months ago - 5 comments

#170 - RuntimeError: expected scalar type Float but found Half

Issue - State: closed - Opened by SanGilbert 3 months ago - 6 comments

#167 - 训练速度超级慢，请问要怎么设置才会提速呢？

Issue - State: closed - Opened by lith0613 3 months ago - 8 comments

#144 - 对于训练代码的建议

Issue - State: closed - Opened by libaolu312 3 months ago - 2 comments
Labels: good first issue

#127 - You simply cache all data in memory, it does not support larger dataset

Issue - State: closed - Opened by StarCycle 3 months ago - 4 comments

#113 - 为什么lora微调后进行推理，会出现这种结果

Issue - State: closed - Opened by SCHfighting 3 months ago - 8 comments

#111 - 3D VAE finetune

Issue - State: closed - Opened by Simona0212 3 months ago - 3 comments

#101 - update finetune multi gpus script

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#99 - Please check that dataloader loads lables from txt failed

Issue - State: closed - Opened by NickPan7779 3 months ago - 1 comment

#98 - Mac max1 14.6 64g内存 跑CogVideoX-2btest.py报错

Issue - State: closed - Opened by chaisheng886 3 months ago - 1 comment

#97 - What optimizer is used to replace the FusedEmaAdam on the NPU device?

Issue - State: closed - Opened by NickPan7779 3 months ago - 5 comments

#96 - Dependency conflict in env preparation

Issue - State: closed - Opened by CodeLyokoscj 3 months ago - 1 comment

#95 - Update Diffusers

Pull Request - State: closed - Opened by Yuan-ManX 3 months ago

#94 - Bug fix

Pull Request - State: closed - Opened by CodeLyokoscj 3 months ago

#92 - CUDA OOM and possible solution -- diffusers cli_demo.py with Nvidia 3090 24GB

Issue - State: closed - Opened by cktlco 3 months ago - 27 comments

#91 - Question about the "Explicit Uniform Sampling" in the report

Issue - State: closed - Opened by StarCycle 3 months ago - 4 comments

#90 - Update GPU Memory Cost to 24GB

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#89 - What does CogVideoX-Pro stand for?

Issue - State: closed - Opened by NieXC 3 months ago - 3 comments

#88 - Great work! when are you planning to release image-to-video models?

Issue - State: closed - Opened by gxd1994 3 months ago - 14 comments

#87 - Why the use of FP16 instead of BF16 precision?

Issue - State: closed - Opened by TheTinyTeddy 3 months ago - 4 comments

#86 - I hope you can share the method of GLM-4 Enhance Prompt

Issue - State: closed - Opened by XksA-me 3 months ago - 2 comments

#85 - About Frame Pack & 3d Rope

Issue - State: closed - Opened by burnquiet 3 months ago - 6 comments

#84 - Is there a demo that supports generating videos from image?

Issue - State: closed - Opened by chenxinhua 3 months ago - 2 comments

#83 - cannot import name 'CogVideoXPipeline' from 'diffusers'

Issue - State: closed - Opened by Hit-ZhangTing 3 months ago - 3 comments

#82 - 补充开发

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#80 - fix

Pull Request - State: closed - Opened by ArtificialZeng 3 months ago - 1 comment

#79 - gram

Pull Request - State: closed - Opened by ArtificialZeng 3 months ago - 1 comment

#78 - Longer video generation

Issue - State: closed - Opened by SutirthaChakraborty 3 months ago - 4 comments

#77 - Update README: Fix `CogVideoX LICENSE` path

Pull Request - State: closed - Opened by kartikeyporwal 3 months ago - 1 comment

#76 - docs: add Japanese README

Pull Request - State: closed - Opened by eltociear 3 months ago - 2 comments

#75 - How to start with 4090？

Issue - State: closed - Opened by shuiyued 3 months ago - 7 comments

#74 - fix: Correct typo in example prompt description

Pull Request - State: closed - Opened by CharlesCNorton 3 months ago

#73 - 对于目前开源代码的疑问

Issue - State: closed - Opened by libaolu312 3 months ago - 10 comments

#72 - On the parallel setting

Issue - State: closed - Opened by X-niper 3 months ago - 2 comments

#71 - Updated README, README_zh, and gradio_demo

Pull Request - State: closed - Opened by yvrjsharma 3 months ago

#70 - Fail to find "sat.mpu", "sat.model" and "sat.training"

Issue - State: closed - Opened by passerby233 3 months ago - 3 comments

#69 - 找不到这个diffusers库

Issue - State: closed - Opened by SCHfighting 3 months ago - 1 comment

#67 - Cogvideox format

Pull Request - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#65 - add Installation

Pull Request - State: closed - Opened by Yuan-ManX 3 months ago - 1 comment

#64 - position embedding

Issue - State: closed - Opened by nankepan 3 months ago - 1 comment

#63 - NPU out of memory

Issue - State: closed - Opened by fallbernana123456 3 months ago - 3 comments

#62 - Add negative prompt

Pull Request - State: closed - Opened by cly2625 3 months ago - 1 comment

#61 - 1

Issue - State: closed - Opened by aeliang 3 months ago

#59 - how to reproduce the demo's generated video quality?

Issue - State: closed - Opened by codeplay0000 3 months ago - 6 comments

#56 - sat 模式依赖下载失败

Issue - State: closed - Opened by dmzlingyin 3 months ago - 2 comments

#55 - original cogvideo

Issue - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#54 - Running on Win10 and 4090

Issue - State: closed - Opened by Yzx-1024 3 months ago - 2 comments

#53 - About Camera Pose Control

Issue - State: closed - Opened by LaFeuilleMorte 3 months ago - 1 comment

#52 - Update README_zh.md

Pull Request - State: closed - Opened by icowan 3 months ago - 1 comment

#51 - OpenAIError

Issue - State: closed - Opened by cklogic 3 months ago - 1 comment

#50 - Details about training data?

Issue - State: closed - Opened by hkunzhe 3 months ago - 5 comments

#49 - Where is the BaseModel?

Issue - State: closed - Opened by xesdiny 3 months ago - 1 comment

#47 - How to image to video?

Issue - State: closed - Opened by MrsZ 3 months ago - 3 comments

#46 - [Q]: Question about the training compute scale

Issue - State: closed - Opened by rlsu9 3 months ago - 2 comments

#44 - test video

Issue - State: closed - Opened by zRzRzRzRzRzRzR 3 months ago

#42 - A segment fault was encountered during inference

Issue - State: closed - Opened by boyu-chen-intern 10 months ago - 1 comment

#41 - It's not working on Hugging Face

Issue - State: closed - Opened by refreshedcyberjohn about 1 year ago - 2 comments