fudan-generative-vision/hallo

Issues

• train_stage2 meet problem: index is out of bounds for dimension

  #197 opened 3 months ago by bingoyesbingoyes
  2

• Artifacts and Lip Sync Issues in Model Training - Seeking Advice from Authors \n 模型训练中的伪影和嘴形同步问题 - 寻求作者建议

  #170 opened 5 months ago by skywalker00001
  3

• 关于测试代码中gradient_checkpointing问题

  #208 opened a month ago by lixinyyang
  1

• 请问这几个weight参数具体影响什么呢，我看不太出来

  #201 opened a month ago by wangqiaoch
  1

• How can this be run on CPU only?

  #168 opened 5 months ago by shahidkarimi
  2

• fatal: unable to access 'https://huggingface.co/fudan-generative-ai/hallo2/': Failed to connect to huggingface.co port 443 after 132846 ms: Connection timed out

  #204 opened 2 months ago by jakeytan
  1

• Can not import hallo node "failed import ModuleNotFoundError: No module named 'audio_separator'

  #187 opened 4 months ago by chchkp
  1

• libcublasLt.so.11: cannot open shared object file: No such file or directory

  #203 opened 2 months ago by fantasy696
  2

• Mandarin checkpoint released （中文权重开源）

  #194 opened 3 months ago by DBDXSS
  2

• The huggingface demo link is broken

  #207 opened a month ago by Phoenix500526
  0

• 请问在resnet里面到底要不要motion模块

  #206 opened a month ago by EveningLin
  0

• Diffusers Issue

  #205 opened 2 months ago by ldavis9000aws
  1

• assert 'detection' in self.models

  #175 opened 5 months ago by ZhangDewei
  2

• Question about reduction=mean when computing loss in train stage 2 ?

  #164 opened 5 months ago by progrobe
  1

• 图片与音频的对齐问题

  #202 opened 2 months ago by wzr0108
  0

• Inquery of Fig.3 in paper

  #200 opened 2 months ago by Nyquist0
  0

• ERROR - root - Failed to execute the training process:

  #199 opened 2 months ago by torracxiaokeai
  3

• Differences in validation metrics

  #198 opened 3 months ago by zhang-haojie
  3

• nan loss occurred in training stage1

  #188 opened 4 months ago by tobepellucid
  1

• Could you please let me know when support for Japanese will be added?

  #178 opened 3 months ago by c0rat1e5
  0

• 报错不能打开face_landmarker_v2_with_blendshapes.task

  #196 opened 3 months ago by dengfenglai321
  0

• 显存恒定9G左右

  #165 opened 5 months ago by Tanwei99
  2

• Misalignment between motion module and AnimateDiff

  #190 opened 4 months ago by Nyquist0
  1

• 是否开源训练数据？

  #193 opened 3 months ago by APeiZou
  1

• Inquiry about frame dim, 16 for inference and 14 for training?

  #192 opened 3 months ago by Nyquist0
  0

• why this hell error?

  #167 opened 5 months ago by shahidkarimi
  1

• mask 类别问题

  #191 opened 4 months ago by DBDXSS
  0

• can I improve the quality of the resulting video? And how to do this?

  #189 opened 4 months ago by Vova-B
  3

• Audio embedding length

  #186 opened 4 months ago by NevermoreCY
  0

• 训练数据集

  #185 opened 4 months ago by Wjc0323
  0

• some bugs when gradient_checkpointing is set True

  #162 opened 5 months ago by progrobe
  2

• stage1和stage2有什么区别呢？

  #184 opened 4 months ago by KnightLancelot
  0

• sync-c和sync-d评价指标如何计算

  #182 opened 4 months ago by hnsywangxin
  2

• Inquiry Regarding Reference Net

  #183 opened 4 months ago by Nyquist0
  1

• About ERROR:root:Failed to execute the training process: name 'str2optimizer8bit_blockwise' is not defined

  #180 opened 4 months ago by HEUfcy
  2

• CUDNN failure 1: CUDNN_STATUS_NOT_INITIALIZED

  #181 opened 4 months ago by Nyquist0
  3

• Link to hallo docker image is broken

  #179 opened 4 months ago by AmoMTL
  0

• About the pretrained checkpoints of Reference Net

  #176 opened 5 months ago by cvipym
  2

• Any problem in improving the model's performance on Mandarin Chinese?

  #177 opened 5 months ago by 2502128021
  0

• about the data cleaning process

  #174 opened 5 months ago by thbupt
  0

• insightface can not pip success

  #173 opened 5 months ago by ZhangDewei
  0

• Which reference picture yields best result?

  #172 opened 5 months ago by NikoBele1
  1

• Failed to execute the training process:

  #171 opened 5 months ago by JianZhang-chick
  1

• Artifacts and Lip Sync Issues in Talking Face Model Training - Seeking Advice from Authors 谈话脸模型训练中的伪影和嘴形同步问题 - 寻求作者建议

  #169 opened 5 months ago by skywalker00001
  0

• The original image had a green background, why did the background change after it was generated?

  #160 opened 5 months ago by liyuli1997
  2

• how to keep the generated video the same size as the original image

  #161 opened 5 months ago by iraymondking
  1

• Some errors in unconditional audio forward

  #163 opened 5 months ago by progrobe
  0

• Please upload a Google Colab Link

  #159 opened 5 months ago by NeuralFalconYT
  0

• train stage1, not use audio feature, only learn the image generation?

  #158 opened 5 months ago by monkeyCv
  1

• How to change the parameters in the py file to train gpu?

  #157 opened 5 months ago by xiaoyu-maka
  3