levihsu/OOTDiffusion

Issues

• VAE解码图像质量损失过大

  #193 opened 4 days ago by DearFloyd
  0

• Is it possible to display an intermediate image of the training process, or to restart training again from the intermediate process?

  #192 opened 4 days ago by gaoming714
  0

• INVALID_PROTOBUF

  #189 opened 11 days ago by rohit22059
  1

• 请问作者训练是在PNDMScheduler，DPMSolverMultistepScheduler 还是默认的DDPMScheduler上训练的？

  #191 opened 6 days ago by af-74413592
  1

• OSError: pretrained_model_name_or_path is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models' If this is a private repository, make sure to pass a token having permission to this repo with `use_auth_token` or log in with `huggingface-cli login`.

  #188 opened 8 days ago by Eminem-lamar
  3

• 是否能够语义控制衣服的尺码，或者在身上的覆盖大小？

  #164 opened 2 months ago by GentlemanHu
  2

• How to find the parsing_atr.onnx file and where?

  #175 opened 10 days ago by annukumari12122002
  1

• Tensorrt conversion of Unet model

  #190 opened 10 days ago by littleGiant-28
  0

• onnx parsing fails

  #183 opened 21 days ago by faculty-hieonn
  6

• How to run code on our own machine

  #187 opened 13 days ago by StyleBotAp
  1

• 报错

  #178 opened a month ago by wbsljy
  1

• 你好，能不能换鞋子和墨镜？

  #180 opened 23 days ago by eswulei
  2

• 有个问题啊,衣服只能越换越多,例如穿长袖的模特就不能换短袖

  #186 opened 18 days ago by FourTest
  0

• IndexError: list index out of range occurs

  #185 opened 19 days ago by mlgbcao666
  0

• How to Create Cloth Mask, Image-Parse, OpenPose-Image, and OpenPose-JSON for Fine-Tuning Model with Custom Dataset?

  #184 opened 20 days ago by Jaynls
  0

• 训练相关疑问

  #182 opened 23 days ago by xuyu666
  0

• 感觉可以做一个image2image的inpaint anything出来

  #181 opened 23 days ago by af-74413592
  1

• torch.cuda.OutOfMemoryError: CUDA out of memory.

  #173 opened a month ago by georgegeorgevan
  4

• 通过秋叶整合包安装，无法识别插件以及节点

  #179 opened a month ago by qiulinj666
  0

• 请问三张4090（24GB）可以对模型进行训练么？

  #176 opened a month ago by xuyu666
  4

• Not Support for Mac？ or M 芯片？

  #177 opened a month ago by hanson-wen
  1

• Defects in dress outputs

  #174 opened a month ago by AnkitSinghBhardwaj
  0

• How do I set device in CUda?

  #147 opened 2 months ago by TanvirHafiz
  5

• “https://ootd.ibot.cn/” cannot access

  #172 opened a month ago by Hanjunzhe
  1

• 报错

  #171 opened a month ago by wbsljy
  1

• multi gpus error

  #170 opened 2 months ago by TigerHH6866
  0

• multi gpu error

  #169 opened 2 months ago by TigerHH6866
  0

• Is it possible to run over CPU?

  #150 opened 2 months ago by danishbansal808
  1

• cuda out of memory even though there is enough free

  #167 opened 2 months ago by DenisSud
  1

• 欢迎发布到wisemodel.cn开源社区

  #168 opened 2 months ago by LiuDQ-wm
  0

• while trainning , Is it correct that these images are generated halfway through the learning...?

  #166 opened 2 months ago by edith-wq
  2

• how to train model with our own dataset

  #153 opened 2 months ago by Jaynls
  2

• Distorted face on outcome result - is there any parameter to control it?

  #165 opened 2 months ago by dimeetrius
  3

• 怎么运行这个项目呢

  #151 opened 2 months ago by eAtSomecoconut
  2

• Inference run time and resources

  #159 opened 2 months ago by dimeetrius
  1

• StableDiffusion prompts or LORA to boost training dataset - help wanted.

  #162 opened 2 months ago by johndpope
  1

• 本地跑的时候 ImportError: cannot import name 'CaptionProjection' from 'diffusers.models.embeddings' (C:\Users\Administrator\AppData\Local\Programs\Python\Python310\lib\site-packages\diffusers\models\embeddings.py)

  #156 opened 2 months ago by psksiu
  2

• 您是指“ https://ootd.ibot.cn/”这个网址重新启动吗，不行，我换台电脑都不行，

  #155 opened 2 months ago by psksiu
  2

• python3.10/site-packages/torch/serialization.py", line 1033, in _legacy_load magic_number = pickle_module.load(f, **pickle_load_args) _pickle.UnpicklingError: invalid load key, 'v'.

  #163 opened 2 months ago by xaviSalazar
  1

• Get error code && INPUT SIZE Unmatched

  #160 opened 2 months ago by Hankerlove
  1

• Generate single best image

  #161 opened 2 months ago by mirfan899
  1

• Any rough estimate on how much it would cost to train it ?

  #157 opened 2 months ago by nitesh-dubey
  5

• /content/OOTDiffusion/checkpoints/humanparsing/parsing_atr.onnx failed. File doesn't exist

  #145 opened 2 months ago by Jaynls
  5

• 请求提供384*512分辨率下的模型权重以进行公平比较

  #158 opened 2 months ago by zwplus
  0

• Downloading: "https://huggingface.co/lllyasviel/Annotators/resolve/main/body_pose_model.pth" 显示没有这个文件

  #154 opened 2 months ago by minmin0516
  1

• https://ootd.ibot.cn/ 用不了了 昨天11点左右开始用不了

  #149 opened 2 months ago by psksiu
  4

• 使用sdxl训练的话，效果会不会更好

  #152 opened 2 months ago by starinskycc
  2

• /content/OOTDiffusion-train/checkpoints/humanparsing/parsing_atr.onnx failed. File doesn't exist

  #146 opened 2 months ago by Jaynls
  3

• Should Original Image be fed to OOT pipeline during inference?

  #144 opened 2 months ago by Ezhil6999
  1

• Hello, what are the characteristics to run the model?

  #148 opened 2 months ago by Jjen95
  0