antgroup/echomimic issues and pull requests

#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 - 19 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

#78 - Accelerated Version of infer_audio2vid.py with Poor Results After Adjustments

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

#77 - 卡会限制吗？

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

#76 - Error when generating video.

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

#75 - Stitch the head back to the body

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

#74 - 生成的视频清晰度问题

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

#73 - 执行demo脚本报错RuntimeError: Failed to import transformers.models.clip.image_processing_clip

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

#72 - Is it possible to batch process target mask .pkl files to reduce VRAM usage?

Issue - State: closed - Opened by Sidd065 4 months ago - 1 comment

#71 - Poor LipSync Quality at lower resolution.

Issue - State: closed - Opened by 345ishaan 4 months ago - 1 comment

#70 - Whats the difference between this and aniportrait?

Issue - State: closed - Opened by G-force78 4 months ago - 3 comments

#69 - 麻烦问下，微调代码有时间计划开源么？感觉使用新的非训练的图片，效果没那么好。

Issue - State: closed - Opened by myhostone1990 4 months ago - 3 comments

#68 - 请问pytorch版本什么要求，安装后报错

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

#67 - 运行python -u infer_audio2vid.py报错

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

#66 - 测试了最新的更新，项目说速度提升10X以上，测试结果，基本上无任何提升

Issue - State: closed - Opened by tgdtu 4 months ago - 5 comments

#64 - FIX: name 'zero_locator_tensor' is not defined

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

#63 - 如何平衡latent上的mse loss 和 pixel空间的spatial loss

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

#62 - Audio driven acceleration not possible?

Issue - State: closed - Opened by kashishnaqvi101 4 months ago - 3 comments

#61 - NameError: name 'zero_locator_tensor' is not defined

Issue - State: closed - Opened by kev123456 4 months ago - 6 comments

#60 - How is 10x acceleration achieved?

Issue - State: closed - Opened by FacePoluke 4 months ago - 7 comments

#59 - Motion Sync not working

Issue - State: closed - Opened by A-2-H 4 months ago - 5 comments

#58 - video 2 video

Issue - State: closed - Opened by prajwal3232 4 months ago - 1 comment

#57 - UNet2DConditionModel参数量不同

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

#56 - About FID/FVD metric

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

#55 - why can inference without landmark

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

#53 - 能否提供多卡推理

Issue - State: closed - Opened by jinghong-6 4 months ago - 2 comments

#52 - 能不能提供提供一个驱动完整图片的功能？或者提供参数只驱动头部区域运动，现在512*512的边缘会运动，使用者无法合成原大小视频

Issue - State: closed - Opened by sunbin728 4 months ago - 4 comments

#51 - python -u webgui.py --server_port=3000报错误No module named 'moviepy'，moviepy已安装

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

#50 - add pose in webgui

Pull Request - State: closed - Opened by Robin021 4 months ago - 1 comment

#49 - CFG Test (Gradio Configuration)

Issue - State: closed - Opened by oisilener1982 4 months ago - 3 comments

#48 - Sample Rate Test (Gradio Configuration)

Issue - State: closed - Opened by oisilener1982 4 months ago - 1 comment

#47 - FPS test (Gradio Configuration)

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

#46 - Trouble with running EchoMimic -- The system cannot find the file specified

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

#45 - Pose-Driven Error

Issue - State: closed - Opened by yhqqxq 4 months ago - 4 comments

#44 - Eye Glitch + Steps Test (Gradio Configuration)

Issue - State: open - Opened by oisilener1982 4 months ago - 6 comments

#43 - Do you have detailed instructions for configuring parameter settings

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

#42 - 这个项目目前最多能推理多长时间的视频呢？

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

#41 - The width and height of the output are inconsistent with the configuration

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

#40 - Pink Artifacts Around Image in Video Rendering

Issue - State: closed - Opened by Galleons2029 4 months ago - 6 comments

#39 - Bat File to 1 Click Open Echo Mimic

Issue - State: open - Opened by oisilener1982 4 months ago - 3 comments

#38 - Question regarding audio features

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

#37 - python -u infer_audio2vid.py, Task been Killed

Issue - State: closed - Opened by BoragoCode 5 months ago

#36 - Pose-Drived Algo Inference not working

Issue - State: open - Opened by nitinmukesh 5 months ago - 4 comments

#35 - Bugs found

Issue - State: closed - Opened by westNeighbor 5 months ago - 4 comments

#34 - 生成帧率过高？

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

#33 - The image stops moving after 48 seconds

Issue - State: closed - Opened by TryingToDoBetter25 5 months ago - 2 comments

#32 - "OpenSSL appears to be unavailable" Error

Issue - State: closed - Opened by TomiTom1234 5 months ago - 1 comment

#31 - Those who are having issues installing EchoMimic

Issue - State: closed - Opened by oisilener1982 5 months ago - 5 comments

#30 - Some weights of the model checkpoint were not used when initializing UNet2DConditionModel:

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

#29 - Automatically get the ffmpeg path

Pull Request - State: closed - Opened by zhtjtcz 5 months ago

#28 - add webgui

Pull Request - State: closed - Opened by Robin021 5 months ago

#27 - Slow Inference

Issue - State: closed - Opened by thanhhung0112 5 months ago - 6 comments

#26 - 视频生成是否可以流式输出

Issue - State: open - Opened by chenhongwu127 5 months ago - 2 comments

#25 - 能否支持全身图片推理，和视频推理这样就很厉害了

Issue - State: closed - Opened by anstonjie 5 months ago - 1 comment

#24 - supports Russian speech

Issue - State: closed - Opened by enjoykian 5 months ago - 1 comment

#23 - add ffmpeg to path

Issue - State: closed - Opened by nitinmukesh 5 months ago - 4 comments

#22 - 做了个 gradio demo 和 jupyter notebook

Issue - State: closed - Opened by O-O1024 5 months ago - 6 comments

#21 - How can I solve this error?

Issue - State: closed - Opened by z497947607 5 months ago - 5 comments

#20 - 运行 python -u infer_audio2vid.py 出现错误 ImportError: cannot import name 'PositionNet' from 'diffusers.models.embeddings' (

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

#19 - Is there anyone who set up the enviroment successfully?

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

#18 - 可以在mac电脑M芯片上面跑吗后期有考虑支持吗

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

#17 - 照片可以为全身照吗

Issue - State: closed - Opened by chenhongwu127 5 months ago - 2 comments

#16 - Train code Release?

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

#15 - 期待提供个docker环境

Issue - State: open - Opened by lonngxiang 5 months ago - 4 comments

#14 - Is this suitable for lipsync?

Issue - State: closed - Opened by xiankgx 5 months ago - 4 comments

#13 - Some weights of the model checkpoint were not used when initializing UNet2DConditionModel

Issue - State: closed - Opened by TryingToDoBetter25 5 months ago - 1 comment

#12 - Please add colab OR HF demo

Issue - State: closed - Opened by s9anus98a 5 months ago - 1 comment

#11 - Any way to prevent the image crop?

Issue - State: closed - Opened by farhanyosuf11 5 months ago - 2 comments

#10 - ImportError: cannot import name 'PositionNet' from 'diffusers.models.embeddings'

Issue - State: closed - Opened by huanggou666 5 months ago - 2 comments

#9 - Is there any way to speed up my test generation time

Issue - State: closed - Opened by su161021 5 months ago - 3 comments

#8 - torchvision::nms的问题已解决出现'float' object has no attribute 'rint'

Issue - State: closed - Opened by hotdogarea 5 months ago - 5 comments

#7 - Will publish a gradio app that has all the features you presented in paper?

Issue - State: closed - Opened by FurkanGozukara 5 months ago - 5 comments

#6 - The paper link is invalid

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

#5 - Any video tutorial how to install ffmpeg-static?

Issue - State: closed - Opened by oisilener1982 5 months ago - 8 comments

#4 - Comfyui nodes? and safetensors?

Issue - State: closed - Opened by GamingDaveUk 5 months ago - 8 comments

GitHub / antgroup/echomimic issues and pull requests