Zejun-Yang/AniPortrait

Issues

• audio2vid脚本生成时报RuntimeError

  #204 opened a month ago
  1

• An alternative project EchoMimicV2 is open-sourced

  #203 opened a month ago
  0

• about train_stage1

  #202 opened a month ago
  0

• Unable to download VFHQ test dataset

  #201 opened a month ago
  0

• 音频时长2分钟，生成视频的时候会报错IndexError index 3450 is out of bounds for axis 0 with size 3450

  #200 opened 2 months ago
  1

• Hyperparameter suggestion for finetuning on new smaller dataset

  #199 opened 2 months ago
  0

• 您好，请问audio2landmark部分的训练代码什么时候发布？

  #198 opened 3 months ago
  0

• size mismatch for PPE.pe

  #197 opened 3 months ago
  3

• Stable Diffusion v1-5的链接404了。最新的在哪里呀

  #196 opened 4 months ago
  3

• module 'ffmpeg' has no attribute 'input'

  #195 opened 4 months ago
  0

• python版本要求还是要3.9才行啊，3.10的版本有些东西就装不上了，希望主页上面要给出python建议版本

  #194 opened 4 months ago
  1

• Collecting av==11.0.0 (from -r requirements.txt (line 2)) 失敗了

  #193 opened 4 months ago
  0

• Hugging Face space duplicated only produces videos of max length of 6 seconds?

  #192 opened 5 months ago
  0

• audio2pose 这一块的设计和 faceformer 很相似，咋没有引用文献呢。

  #191 opened 5 months ago
  0

• How to obtain neutral mesh during audio2mesh training?

  #190 opened 5 months ago
  0

• 单卡GPU 需要多大内存能跑起来

  #189 opened 5 months ago
  2

• 生成问题

  #188 opened 5 months ago
  0

• which languages can be supported?

  #187 opened 5 months ago
  0

• 请问支持宠物吗

  #186 opened 5 months ago
  0

• An alternative project EchoMimic is open-sourced

  #185 opened 6 months ago
  0

• 关于生成视频抖动

  #184 opened 6 months ago
  0

• audio-driven, self-driven, Face reenacment 这三者有什么区别？

  #183 opened 6 months ago
  0

• About stage1 training steps

  #182 opened 6 months ago
  0

• 请问，这是练丹练坏了吗？

  #181 opened 6 months ago
  1

• Gradio webUI error

  #180 opened 6 months ago
  0

• python 的script执行命令行，能不能添加以下参数说明阿，生成的视频默认是左中右三段式的，怎么能生成单独的三个视频？

  #179 opened 6 months ago
  0

• Extract 6d pose sequence and train audio2pose model?

  #178 opened 6 months ago
  0

• 如何通过 bs 控制表情

  #177 opened 6 months ago
  0

• ModuleNotFoundError: No module named 'diffusers.models.dual_transformer_2d'

  #176 opened 6 months ago
  2

• 关于Stage2训练问题

  #175 opened 6 months ago
  1

• 端口号可以改么

  #174 opened 6 months ago
  0

• 请问推理至少需要多少显存？

  #173 opened 6 months ago
  1

• 多张低显存卡解决方案是否存在

  #172 opened 6 months ago
  1

• Audio2Vid输出尺寸

  #171 opened 7 months ago
  2

• Confusion over pose_guider.py, seems that there's no cross attention between ref pose and target pose.

  #170 opened 7 months ago
  1

• Gradio Web UI example failed

  #169 opened 7 months ago
  1

• HuggingFace demo occurred error

  #168 opened 7 months ago
  1

• Body movements + jittery + artifacts issues

  #167 opened 7 months ago
  2

• 有个训练的小问题请问下作者大大

  #166 opened 7 months ago
  2

• 请问audio2landmark部分的训练代码会开源吗？

  #165 opened 7 months ago
  2

• Error occurred when executing AniPortraitRun: [Errno 2] No such file or directory: ''

  #163 opened 7 months ago
  1

• Bug in train_stage_1.py, causing list out of range

  #162 opened 7 months ago
  2

• Reaching EMO level quality

  #161 opened 7 months ago
  1

• ffmpeg error

  #160 opened 7 months ago
  2

• X-portrait as source to improve aniportrait

  #159 opened 7 months ago
  1

• ReferenceNet Model in the Stage1

  #158 opened 7 months ago
  1

• SDXL Support?

  #157 opened 7 months ago
  2

• 生成时间真的很长很慢

  #153 opened 7 months ago
  0

• 请问audio2video中，最多支持多长时间的audio输入？

  #152 opened 7 months ago
  4

• Will it be possible to use its API somehow?

  #151 opened 7 months ago
  2