本地搭建NovelAi (免费的色图生成器，可用colab在线运行)

Colter23

@XCWQW1 （在 taming-transformers 项目目录下运行 git init
然后运行 git remote add origin https://github.com/CompVis/taming-transformers.git

XCWQW1

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

@XCWQW1 （在 taming-transformers 项目目录下运行 git init
然后运行 git remote add origin https://github.com/CompVis/taming-transformers.git

OK我试试去

XCWQW1

@Colter23 在git cmd 下
D:\stable-diffusion-webui-master\repositories\taming-transformers>git remote add origin https://github.com/CompVis/taming-transformers.git
fatal: not a git repository (or any of the parent directories): .git

D:\stable-diffusion-webui-master\repositories\taming-transformers>
还是一样的提示啊 why

Colter23

@XCWQW1 先执行 git init 啊。。。

XCWQW1

@Colter23 我眼瞎了，现在成这样了：
venv "D:\stable-diffusion-webui-master\venv\Scripts\Python.exe"
Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]
Commit hash: <none>
Traceback (most recent call last):
File "D:\stable-diffusion-webui-master\launch.py", line 164, in <module>
prepare_enviroment()
File "D:\stable-diffusion-webui-master\launch.py", line 140, in prepare_enviroment
git_clone("https://github.com/CompVis/taming-transformers.git", repo_dir('taming-transformers'), "Taming Transformers", taming_transformers_commit_hash)
File "D:\stable-diffusion-webui-master\launch.py", line 74, in git_clone
current_hash = run(f'"{git}" -C {dir} rev-parse HEAD', None, f"Couldn't determine {name}'s hash: {commithash}").strip()
File "D:\stable-diffusion-webui-master\launch.py", line 32, in run
raise RuntimeError(message)
RuntimeError: Couldn't determine Taming Transformers's hash: 24268930bf1dce879235a7fddd0b2355b84d7ea6.
Command: "git" -C repositories\taming-transformers rev-parse HEAD
Error code: 128
stdout: HEAD

stderr: fatal: ambiguous argument 'HEAD': unknown revision or path not in the working tree.
Use '--' to separate paths from revisions, like this:
'git <command> [<revision>...] -- [<file>...]'

请按任意键继续. . .

y1052895290

@Colter23 那就不明白了，按理说我12700和1080都是兼容的，torch就是抓不到显卡

lidadadada

大佬，求放gdrive link呀，pruned版的可以下载了，求个完整版，magnet没资源呀

LookStars

@Colter23
venv "C:\Users\zlr75\stable-diffusion-webui\venv\Scripts\Python.exe"
Python 3.10.7 (tags/v3.10.7:6cc6b13, Sep 5 2022, 14:08:36) [MSC v.1933 64 bit (AMD64)]
Commit hash: d5c14365fd468dbf89fa12a68bea5b217077273c
Installing requirements for Web UI
Launching Web UI with arguments: --disable-safe-unpickle
LatentDiffusion: Running in eps-prediction mode
DiffusionWrapper has 859.52 M params.
making attention of type 'vanilla' with 512 in_channels
Working with z of shape (1, 4, 32, 32) = 4096 dimensions.
making attention of type 'vanilla' with 512 in_channels
Traceback (most recent call last):
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 392, in load_state_dict
return torch.load(checkpoint_file, map_location="cpu")
File "C:\Users\zlr75\stable-diffusion-webui\modules\safe.py", line 89, in load
return unsafe_torch_load(filename, *args, **kwargs)
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 705, in load
with _open_zipfile_reader(opened_file) as opened_zipfile:
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\torch\serialization.py", line 242, in init
super(_open_zipfile_reader, self).init(torch._C.PyTorchFileReader(name_or_buffer))
RuntimeError: PytorchStreamReader failed reading zip archive: failed finding central directory

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 396, in load_state_dict
if f.read().startswith("version"):
UnicodeDecodeError: 'gbk' codec can't decode byte 0x80 in position 64: illegal multibyte sequence

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
File "C:\Users\zlr75\stable-diffusion-webui\launch.py", line 165, in <module>
start_webui()
File "C:\Users\zlr75\stable-diffusion-webui\launch.py", line 159, in start_webui
import webui
File "C:\Users\zlr75\stable-diffusion-webui\webui.py", line 82, in <module>
shared.sd_model = modules.sd_models.load_model()
File "C:\Users\zlr75\stable-diffusion-webui\modules\sd_models.py", line 177, in load_model
sd_model = instantiate_from_config(sd_config.model)
File "C:\Users\zlr75\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "C:\Users\zlr75\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 461, in init
self.instantiate_cond_stage(cond_stage_config)
File "C:\Users\zlr75\stable-diffusion-webui\repositories\stable-diffusion\ldm\models\diffusion\ddpm.py", line 519, in instantiate_cond_stage
model = instantiate_from_config(config)
File "C:\Users\zlr75\stable-diffusion-webui\repositories\stable-diffusion\ldm\util.py", line 85, in instantiate_from_config
return get_obj_from_str(config["target"])(**config.get("params", dict()))
File "C:\Users\zlr75\stable-diffusion-webui\repositories\stable-diffusion\ldm\modules\encoders\modules.py", line 142, in init
self.transformer = CLIPTextModel.from_pretrained(version)
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 1978, in from_pretrained
state_dict = load_state_dict(resolved_archive_file)
File "C:\Users\zlr75\stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py", line 408, in load_state_dict
raise OSError(
OSError: Unable to load weights from pytorch checkpoint file for 'C:\Users\zlr75/.cache\huggingface\transformers\c506559a5367a918bab46c39c79af91ab88846b49c8abd9d09e699ae067505c6.6365d436cc844f2f2b4885629b559d8ff0938ac484c01a6796538b2665de96c7' at 'C:\Users\zlr75/.cache\huggingface\transformers\c506559a5367a918bab46c39c79af91ab88846b49c8abd9d09e699ae067505c6.6365d436cc844f2f2b4885629b559d8ff0938ac484c01a6796538b2665de96c7'. If you tried to load a PyTorch model from a TF 2.0 checkpoint, please set from_tf=True.
请按任意键继续. . .
参考了您的解决方案报的错
git pull重新尝试报错
加入参数重试报错
这里是加入参数后报的错

LookStars

猜测...估计就是大佬所说的更新问题，大概率是需要等开发者解决这个问题

LookStars

如果是更新问题那是不是可以下载之前的版本...

lidadadada

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

大佬，求放gdrive link呀，pruned版的可以下载了，求个完整版，magnet没资源呀

hypernetworks.zip也请给个gdrive 链接吧，gdrive用https://drive.google.com/file/d/xxxxxx/view 这种方式还是可以下载的。感谢感谢~

leklueze

@LookStars
这个我在 “stable-diffusion-webui\venv\lib\site-packages\transformers\modeling_utils.py” 这里搜 from_tf ，把False改成True，过去了，然后后面又卡在

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'

这里了...

XCWQW1

@lidadadada 你要吗有IPV6你从我这下
我软路由的aria2昨天下午刚下完的磁力链接
要你加下我QQ 3539757707

kouki

@LookStars 我的问题和这个一模一样，后来在寻找解的时候注意到了报错中还包含了非目录的路径，我跟着摸进去后看到了乱码文件，我把他们删除后重启就继续下载了
我的：C:\Users\Administrator.cache\huggingface\transformers
应该是你的：C:\Users\zlr75/.cache\huggingface\transformers

Alalajiyh

@Colter23 感谢！升级后已经成功了！

Alalajiyh

@LookStars 是的，升级后解决了！

kouki

为什么，，，为什么会变成这个样子呜
06)G(S6(0}32INLPWWE@$X0.png

Little zerii

@Colter23 这是不是只能升级显卡了

Colter23

@XCWQW1 具体的我也不知道，可能是因为你手动下载zip的方式放置的库。你可尝试使用 git clone 指令来安装库。github上有个跟你类似的情况，但还没有解决 https://github.com/AUTOMATIC1111/stable-diffusion-webui/issues/2247