BadToBest/EchoMimic issues and pull requests

#172 - 为什么用绿色背景推理出来得视频带有光晕

Issue - State: open - Opened by llybood about 1 month ago

#171 - 50秒以后人物不动了

Issue - State: closed - Opened by poyingshihuang about 1 month ago

#170 - ValueError: When localhost is not accessible, a shareable link must be created. Please set share=True or check your proxy settings to allow access to localhost.

Issue - State: closed - Opened by poyingshihuang about 1 month ago

#169 - quality drop with non 512x512 width and height (非512x512大小的输出质量变差）

Issue - State: open - Opened by RockySong about 1 month ago - 1 comment

#168 - Heavy Head Movement and bad Mouth/Teeth ?

Issue - State: open - Opened by lost-in-emotions about 1 month ago

#167 - Workaround for the Setting Parameters ?

Issue - State: open - Opened by lost-in-emotions about 1 month ago

#166 - 运行所有指令都出现killed

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

#165 - is it possible to render with liveportrait backend

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

#164 - Validation details

Issue - State: open - Opened by zhang-haojie about 2 months ago

#163 - Getting issue in 'src\models\unet_2d_blocks.py' DownEncoderBlock2D does not exist

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

#162 - Slow speed on V100

Issue - State: open - Opened by CurrenWong about 2 months ago - 1 comment

#161 - 只能支持512x512的，什么时候可以支持其他比例

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

#160 - Is there any plan for releasing the training code?

Issue - State: open - Opened by foreverhell about 2 months ago

#159 - 超过一分钟的长视频合成后，视频后半部分黑屏

Issue - State: open - Opened by TonyEiven 2 months ago - 1 comment

#158 - Error

Issue - State: open - Opened by malc27 2 months ago

#157 - Video to video?

Issue - State: open - Opened by G-force78 2 months ago - 1 comment

#156 - 训练数据有开源的计划吗？

Issue - State: open - Opened by APeiZou 2 months ago

#155 - 请问执行是怎么回事。这个问题出在哪里。

Issue - State: open - Opened by laochendeai 2 months ago - 1 comment

#154 - Cuda out of memory on RTX 3090 24gb

Issue - State: closed - Opened by ChanHyeok-Choi 2 months ago - 8 comments

#153 - ERROR WHEN USE THE GUI

Issue - State: open - Opened by lior007 2 months ago - 1 comment

#152 - 生成的视频为啥抖的厉害

Issue - State: open - Opened by lianping1985 2 months ago - 4 comments

#151 - webgui.py代码写得有点问题，需要自行修改才能跑起来

Issue - State: open - Opened by huanglong123 2 months ago - 1 comment

#150 - EchoMimic推理视频贴回原视频的方法分享

Issue - State: open - Opened by zzk88862 2 months ago - 2 comments

#149 - test splits for the evaluation datasets

Issue - State: open - Opened by juvekaradheesh 3 months ago

#148 - HuggingFace Error

Issue - State: open - Opened by anwarrassool 3 months ago

#147 - About Conditions for Inference and Training

Issue - State: open - Opened by Shelton0215 3 months ago

#146 - 关于在您的推理代码中音频处理的一个问题

Issue - State: open - Opened by FucK5t4r 3 months ago

#145 - Bad result in webui

Issue - State: open - Opened by XeoOuYang 3 months ago - 3 comments

#144 - low vram model request

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

#143 - memory leakage

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

#142 - 执行报错:The size of tensor a (64) must match the size of tensor b (128) at non-singleton dimension 4

Issue - State: open - Opened by yeohx 3 months ago - 6 comments

#141 - CUDA out of memory. :( no hugging face no colab

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

#140 - What is the algorithm of accelation ?

Issue - State: open - Opened by EmmaThompson123 3 months ago - 1 comment

#139 - 最低硬件要求多大?

Issue - State: open - Opened by yeohx 3 months ago - 2 comments

#138 - 为什么我生成出来的视频是黑屏的？

Issue - State: open - Opened by shengming1230 3 months ago - 4 comments

#137 - A bug was found here, some jpeg format found no face here

Issue - State: open - Opened by XeoOuYang 3 months ago - 2 comments

#136 - Cannot process type as video: <class 'pathlib.WindowsPath'>

Issue - State: open - Opened by HandsomeDong 3 months ago - 1 comment

#135 - 无法在mac m2 安装？

Issue - State: open - Opened by xkyang1 3 months ago

#134 - 安装依赖报错

Issue - State: open - Opened by yeohx 3 months ago - 1 comment

#133 - 可以设置人物头部不晃动吗

Issue - State: closed - Opened by ppx0001 3 months ago - 1 comment

#132 - Bearded faces aren't pretrained, either expose the datasets so that we can train it

Issue - State: open - Opened by rahuljustbaat 3 months ago - 1 comment

#131 - inference speed is very very poor of echomimic

Issue - State: open - Opened by Arvrairobo 3 months ago - 2 comments

#130 - pretrained_weights的下载地址好像没有了

Issue - State: open - Opened by RAYaaaaaaaaaaaaa 3 months ago - 3 comments

#129 - 想问下Demo里面图片来源？

Issue - State: open - Opened by WaterMinding 3 months ago

#128 - Processing image got a critical error when running this webgui.py

Issue - State: open - Opened by pli2014 3 months ago - 5 comments

#127 - Fix the bug in the inference

Pull Request - State: open - Opened by Guohanzhong 3 months ago - 1 comment

#126 - 推理，一台v100 只能实现一个并发吗多并发只能多机器吗

Issue - State: open - Opened by mayu123mayu 3 months ago - 1 comment

#125 - 加速问题

Issue - State: open - Opened by YSLLYW 3 months ago - 1 comment

#124 - not good output with beard faces, beard gets blurry, please train beard faces

Issue - State: open - Opened by rahuljustbaat 3 months ago

#123 - 小白用户依赖包版本没有弄好.安装了一星期没成功.

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

#122 - 有哪位知道如何才能不裁剪

Issue - State: closed - Opened by wsy6566 3 months ago - 2 comments

#121 - Error:Segmentation fault (core dumped)

Issue - State: open - Opened by zjulkw 3 months ago - 1 comment

#120 - 是否支持仅编辑视频中人脸嘴巴区域，而不更改头部运动/眼睛睁闭呢？

Issue - State: open - Opened by gobigrassland 3 months ago - 1 comment

#119 - Refinement for gpu settings

Pull Request - State: open - Opened by CodeLyokoscj 3 months ago - 1 comment

#118 - Question about the accelerate times

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

#117 - 高清数据集 Large-Scale and High-resolution Chinese-Based Talking Head Dataset 100G

Issue - State: open - Opened by moming133 3 months ago

#116 - Missing stt

Issue - State: open - Opened by jmanhype 3 months ago

#115 - beard is getting blurry and distorted

Issue - State: open - Opened by rahuljustbaat 4 months ago

#114 - fix cv2 Bad arguments in resize

Pull Request - State: open - Opened by lingfengchencn 4 months ago - 2 comments

#113 - diffusers版本问题

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

#112 - output is blurry and not HD despite the input image being HD

Issue - State: open - Opened by rahuljustbaat 4 months ago

#111 - 对于图片的适配好像有问题

Issue - State: open - Opened by coderlihong 4 months ago - 3 comments

#110 - Pose driven inference

Issue - State: open - Opened by alasokolova 4 months ago - 2 comments

#109 - Full body talking video?

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

#108 - 执行python -u infer_audio2vid.py 报错:No module named 'cv2'

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

#107 - How do you accelerate the inference?

Issue - State: open - Opened by xumingw 4 months ago

#106 - Difference between reference_unet and reference_unet_pose

Issue - State: open - Opened by antonibigata 4 months ago

#105 - How to get facial landmarks？

Issue - State: open - Opened by KleinXin 4 months ago - 1 comment

#104 - Getting below issue, please help git lfs pull is in just downloading, how many gb?

Issue - State: closed - Opened by rahuljustbaat 4 months ago

#103 - audio&pose-drived generate multi-hand result

Issue - State: open - Opened by superstring 4 months ago

#102 - Help guys “”face_img = cv2.resize(face_img, (width, height))“” webui issue.

Issue - State: open - Opened by Softysoftyball 4 months ago - 3 comments

#101 - 为什么face_locator_tensor 这么慢呀。。。69s一步

Issue - State: open - Opened by 3682483 4 months ago - 6 comments

#100 - Create webgui_a2v_acc.py

Pull Request - State: closed - Opened by newgenai79 4 months ago - 1 comment

#99 - Please delete

Issue - State: closed - Opened by nitinmukesh 4 months ago

#98 - 流式生成带alpha通道的视频，让视频背景可以透明，仅保留人物，这将是未来的必备的一个功能趋势！！！

Issue - State: open - Opened by steamed-bun-with-brown-sugar 4 months ago - 2 comments

#97 - Add a blinking option

Issue - State: open - Opened by G-force78 4 months ago

#96 - Support for Selected Landmark

Issue - State: open - Opened by 345ishaan 4 months ago

#95 - FileNotFoundError: [Errno 2] No such file or directory: './pretrained_weights/denoising_unet_acc.pth'

Issue - State: closed - Opened by oisilener1982 4 months ago - 2 comments

#94 - motion_sync skipped. Please replace the pose dir with the driven video to enable it.

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

#93 - 如果video_length超过face_mask_tensor的长度会崩溃

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

#92 - 请问一下没有N卡的机器可以启动服务么?

Issue - State: open - Opened by yeohx 4 months ago

#91 - no './assets/mask_image_512.png'

Issue - State: open - Opened by ShungJhon 4 months ago

#90 - 启动webgui.py，上传图片和音频后报错

Issue - State: open - Opened by hjj-lmx 4 months ago - 18 comments

#90 - 启动webgui.py，上传图片和音频后报错

Issue - State: open - Opened by hjj-lmx 4 months ago - 18 comments

#89 - Release Dataset?

Issue - State: closed - Opened by JZArray 4 months ago - 1 comment

#88 - 请问怎么在webUI中使用infra_ audio2vid acc. py？

Issue - State: open - Opened by TryingToDoBetter25 4 months ago

#87 - 如何使用指定GPU进行推理

Issue - State: closed - Opened by ppx0001 4 months ago - 1 comment

#86 - 如何使用多GPU推理

Issue - State: closed - Opened by ppx0001 4 months ago - 1 comment

#85 - 发现两个问题

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

#84 - 音频与关键点作为条件驱动问题

Issue - State: closed - Opened by gobigrassland 4 months ago - 1 comment

#83 - 头像晃动幅度怎么调小？

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

#82 - 上传四分钟的音频合出来好像只有前面10s，后面的图片就不会动了

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

#81 - 能不能不要裁切上传的图片？

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

#80 - 音频驱动有加速吗？

Issue - State: closed - Opened by yanglibo0512 4 months ago - 2 comments

#79 - Fix undefined variable error in pipeline_echo_mimic.py

Pull Request - State: open - Opened by touchwolf 4 months ago

GitHub / BadToBest/EchoMimic issues and pull requests