MiraiForum

    • Register
    • Login
    • Search
    • Popular
    • Recent
    • Unsolved
    • Tags
    • Groups
    • 友情链接

    本地搭建NovelAi (免费的色图生成器,可用colab在线运行)

    技术交流板块
    novelai ai 图像生成 色图
    47
    226
    84877
    Loading More Posts
    • Oldest to Newest
    • Newest to Oldest
    • Most Votes
    Reply
    • Reply as topic
    Log in to reply
    This topic has been deleted. Only users with topic management privileges can see it.
    • kouki
      kouki @LookStars last edited by

      @LookStars 相同问题,就等大佬解决#安详

      1 Reply Last reply Reply Quote 0
      • L
        loveriswmy last edited by

        fe9ec343-6de7-466b-bee5-997d15417cb0-image.png
        大佬这个问题卡住了求带5555

        Colter23 L 2 Replies Last reply Reply Quote 0
        • L
          leklueze @LookStars last edited by

          @LookStars 在 本地搭建NovelAi (免费的色图生成器,可用colab在线运行) 中说:

          c506559a5367a918bab46c39c79af91ab88846b49c8abd

          我也是报相同错误,找到那个临时文件zip打不开

          1 Reply Last reply Reply Quote 0
          • Colter23
            Colter23 @LookStars last edited by Colter23

            @LookStars @leklueze @kouki 再更新一下webui项目试试 git pull。如果还不行的话那去在 webui-user.bat 文件里,在 COMMANDLINE_ARGS= 后面加上 --disable-safe-unpickle 这个参数试试(这个问题是后面更新导致的,之前都没有safe.py这个文件,具体这个是干什么用的我也不知道

            L LookStars 3 Replies Last reply Reply Quote 0
            • Colter23
              Colter23 @Little zerii last edited by

              @Little-zerii RuntimeError: CUDA out of memory. 这就是显存溢出了

              L 1 Reply Last reply Reply Quote 0
              • Colter23
                Colter23 @No_V last edited by

                @No_V 你python啥版本的,如果不是 3.10 的话就再安个 3.10 (或者你有没有切换pip的镜像地址?

                N 1 Reply Last reply Reply Quote 0
                • Colter23
                  Colter23 @Alalajiyh last edited by

                  @Alalajiyh 升级下python(需要3.10

                  A 1 Reply Last reply Reply Quote 0
                  • N
                    No_V @Colter23 last edited by

                    @Colter23 换了个镜像源好了

                    1 Reply Last reply Reply Quote 0
                    • Colter23
                      Colter23 @loveriswmy last edited by

                      @loveriswmy 先更新下项目git pull, 再运行 ./venv/Scripts/pip.exe install -r ./requirements.txt 安装依赖

                      Colter23 1 Reply Last reply Reply Quote 1
                      • X
                        XCWQW1 last edited by

                        QQ截图20221011102205.png 大佬这咋办

                        Colter23 1 Reply Last reply Reply Quote 0
                        • L
                          leklueze @Colter23 last edited by leklueze

                          @Colter23
                          大哥,之前的问题解决了,后面又出

                          Loading a TensorFlow model in PyTorch, requires both PyTorch and TensorFlow to be installed. Please see https://pytorch.org/ and https://www.tensorflow.org/install/ for installation instructions.
                          Traceback (most recent call last):
                          File "F:\Project\AI\stable-diffusion-webui-master\launch.py", line 165, in <module>
                          start_webui()
                          File "F:\Project\AI\stable-diffusion-webui-master\launch.py", line 159, in start_webui
                          import webui
                          File "F:\Project\AI\stable-diffusion-webui-master\webui.py", line 82, in <module>
                          shared.sd_model = modules.sd_models.load_model()
                          File "F:\Project\AI\stable-diffusion-webui-master\modules\sd_models.py", line 174, in load_model
                          sd_model = instantiate_from_config(sd_config.model)
                          File "F:\Project\AI\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
                          return get_obj_from_str(config["target"])(**config.get("params", dict()))
                          File "F:\Project\AI\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 461, in init
                          self.instantiate_cond_stage(cond_stage_config)
                          File "F:\Project\AI\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 519, in instantiate_cond_stage
                          model = instantiate_from_config(config)
                          File "F:\Project\AI\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
                          return get_obj_from_str(config["target"])(**config.get("params", dict()))
                          File "F:\Project\AI\stable-diffusion-webui-master\repositories\stable-diffusion\ldm\modules\encoders\modules.py", line 142, in init
                          self.transformer = CLIPTextModel.from_pretrained(version)
                          File "F:\Project\AI\stable-diffusion-webui-master\venv\lib\site-packages\transformers\modeling_utils.py", line 2035, in from_pretrained
                          model = load_tf2_checkpoint_in_pytorch_model(model, resolved_archive_file, allow_missing_keys=True)
                          File "F:\Project\AI\stable-diffusion-webui-master\venv\lib\site-packages\transformers\modeling_tf_pytorch_utils.py", line 293, in load_tf2_checkpoint_in_pytorch_model
                          import tensorflow as tf # noqa: F401
                          ModuleNotFoundError: No module named 'tensorflow'

                          之前我自己装的时候就遇到这问题没法解决,整个删了按您的教程重装,又遇到这问题了

                          1 Reply Last reply Reply Quote 0
                          • Colter23
                            Colter23 @Colter23 last edited by

                            @Colter23 在 本地搭建NovelAi (免费的色图生成器,可用colab在线运行) 中说:

                            先更新下项目git pull, 再运行 ./venv/Scripts/pip.exe install -r ./requirements.txt 安装依赖

                            @leklueze 试试

                            1 Reply Last reply Reply Quote 0
                            • Colter23
                              Colter23 @XCWQW1 last edited by

                              @XCWQW1 在项目根目录找到 repositories 文件夹,没有就自己建一个。
                              进去之后运行 git clone https://github.com/CompVis/taming-transformers.git

                              X 1 Reply Last reply Reply Quote 0
                              • X
                                XCWQW1 @Colter23 last edited by

                                @Colter23 从github上下载后放入文件夹内了已经

                                1 Reply Last reply Reply Quote 0
                                • Y
                                  y1052895290 last edited by

                                  还是torch抓不到显卡的问题,我在gh那边这个issue的串里也回复了,会不会是win11的锅?

                                  Colter23 1 Reply Last reply Reply Quote 0
                                  • Colter23
                                    Colter23 @y1052895290 last edited by

                                    @y1052895290 我就是win11

                                    Y 1 Reply Last reply Reply Quote 0
                                    • Colter23
                                      Colter23 @StageGuard last edited by

                                      @StageGuard 麻了(跳进个大坑属实是

                                      X 1 Reply Last reply Reply Quote 0
                                      • X
                                        XCWQW1 @Colter23 last edited by

                                        @Colter23 我下完还是一样(

                                        Colter23 1 Reply Last reply Reply Quote 0
                                        • Colter23
                                          Colter23 @XCWQW1 last edited by

                                          @XCWQW1 你咋下的,用的git指令还是下的压缩包

                                          X 1 Reply Last reply Reply Quote 0
                                          • X
                                            XCWQW1 @Colter23 last edited by

                                            @Colter23 下的压缩包

                                            Colter23 1 Reply Last reply Reply Quote 0
                                            • 1
                                            • 2
                                            • 3
                                            • 4
                                            • 5
                                            • 6
                                            • 7
                                            • 11
                                            • 12
                                            • 5 / 12
                                            • First post
                                              Last post
                                            Powered by Mamoe Technologies & NodeBB | 友情链接 | 服务监控 | Contact