ColorFlow - 清华联合腾讯开源，自动给黑白照片、漫画上色，保持角色一致性模型 本地一键整合包下载

At***

  warnings.warn(_BETA_TRANSFORMS_WARNING)
Traceback (most recent call last):
  File "<frozen __main__>", line 3, in <module>
  File "<frozen app>", line 47, in <module>
ImportError: cannot import name 'AutoencoderKL' from 'diffusers' (unknown location)
请按任意键继续. . .

4090同无法启动

jay***

补丁打了又出来个这个                                                                                                           
RuntimeError: Failed to import diffusers.models.autoencoders.autoencoder_kl because of the following error (look up to see its traceback):
module 'torch' has no attribute 'float8_e4m3fn'
请按任意键继续. . .

CY***

Traceback (most recent call last):
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\utils\import_utils.py", line 920, in _get_module
    return importlib.import_module("." + module_name, self.__name__)
  File "E:\ColorFlow\deepface\lib\importlib\__init__.py", line 127, in import_module
    return _bootstrap._gcd_import(name[level:], package, level)
  File "<frozen importlib._bootstrap>", line 1014, in _gcd_import
  File "<frozen importlib._bootstrap>", line 991, in _find_and_load
  File "<frozen importlib._bootstrap>", line 961, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "<frozen importlib._bootstrap>", line 1014, in _gcd_import
  File "<frozen importlib._bootstrap>", line 991, in _find_and_load
  File "<frozen importlib._bootstrap>", line 975, in _find_and_load_unlocked
  File "<frozen importlib._bootstrap>", line 671, in _load_unlocked
  File "<frozen importlib._bootstrap_external>", line 783, in exec_module
  File "<frozen importlib._bootstrap>", line 219, in _call_with_frames_removed
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\models\autoencoders\__init__.py", line 1, in <module>
    from .autoencoder_asym_kl import AsymmetricAutoencoderKL
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\models\autoencoders\autoencoder_asym_kl.py", line 22, in <module>
    from ..modeling_utils import ModelMixin
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\models\modeling_utils.py", line 35, in <module>
    from ..quantizers import DiffusersAutoQuantizer, DiffusersQuantizer
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\quantizers\__init__.py", line 15, in <module>
    from .auto import DiffusersAutoQuantizer
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\quantizers\auto.py", line 31, in <module>
    from .torchao import TorchAoHfQuantizer
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\quantizers\torchao\__init__.py", line 15, in <module>
    from .torchao_quantizer import TorchAoHfQuantizer
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\quantizers\torchao\torchao_quantizer.py", line 57, in <module>
    torch.float8_e4m3fn,
AttributeError: module 'torch' has no attribute 'float8_e4m3fn'

The above exception was the direct cause of the following exception:

Traceback (most recent call last):
  File "<frozen __main__>", line 3, in <module>
  File "<frozen app>", line 47, in <module>
  File "<frozen importlib._bootstrap>", line 1039, in _handle_fromlist
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\utils\import_utils.py", line 911, in __getattr__
    value = getattr(module, name)
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\utils\import_utils.py", line 910, in __getattr__
    module = self._get_module(self._class_to_module[name])
  File "E:\ColorFlow\deepface\lib\site-packages\diffusers\utils\import_utils.py", line 922, in _get_module
    raise RuntimeError(
RuntimeError: Failed to import diffusers.models.autoencoders.autoencoder_kl because of the following error (look up to see its traceback):
module 'torch' has no attribute 'float8_e4m3fn'
请按任意键继续. . .
已经下载补丁了，还是这样

五帝***

5060ti 16G

luju***

确实很不错，特别是保持角色的一致性

23565***

这个可以有，谢谢分享

14022***

5090是不是用不了？

14022***

5090d用不了

ImportError: peft>=0.15.0 is required for a normal functioning of this module, but found peft==0.13.2.

hypo***

     :::::::::       ::::::::::       ::::::::::       :::::::::       ::::::::::           :::        ::::::::       ::::::::::
    :+:    :+:      :+:              :+:              :+:    :+:      :+:                :+: :+:     :+:    :+:      :+:
   +:+    +:+      +:+              +:+              +:+    +:+      +:+               +:+   +:+    +:+             +:+
  +#+    +:+      +#++:++#         +#++:++#         +#++:++#+       :#::+::#         +#++:++#++:   +#+             +#++:++#
+#+    +#+      +#+              +#+              +#+             +#+              +#+     +#+   +#+             +#+
#+#    #+#      #+#              #+#              #+#             #+#              #+#     #+#   #+#    #+#      #+#
#########       ##########       ##########       ###             ###              ###     ###    ########       ##########
-----------------------------------------------------
更多实用好玩的AI应用，访问 https://deepface.cc
软件WebUI正在启动中，请稍后...
-----------------------------------------------------
H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\torchvision\datapoints\__init__.py:12: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
  warnings.warn(_BETA_TRANSFORMS_WARNING)
H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\torchvision\transforms\v2\__init__.py:54: UserWarning: The torchvision.datapoints and torchvision.transforms.v2 namespaces are still Beta. While we do not expect major breaking changes, some APIs may still change according to user feedback. Please submit any feedback you may have in this issue: https://github.com/pytorch/vision/issues/6753, and you can also check out https://github.com/pytorch/vision/issues/7319 to learn more about the APIs that we suspect might involve future changes. You can silence this warning by calling torchvision.disable_beta_transforms_warning().
  warnings.warn(_BETA_TRANSFORMS_WARNING)
Traceback (most recent call last):
  File "<frozen __main__>", line 3, in <module>
  File "<frozen app>", line 46, in <module>
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\__init__.py", line 5, in <module>
    from .utils import (
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\utils\__init__.py", line 21, in <module>
    from .constants import (
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\utils\constants.py", line 63, in <module>
    dep_version_check("peft")
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\dependency_versions_check.py", line 34, in dep_version_check
    require_version(deps[pkg], hint)
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\utils\versions.py", line 111, in require_version
    _compare_versions(op, got_ver, want_ver, requirement, pkg, hint)
  File "H:\image\11111\11111\ColorFlow\deepface\lib\site-packages\diffusers\utils\versions.py", line 44, in _compare_versions
    raise ImportError(
ImportError: peft>=0.17.0 is required for a normal functioning of this module, but found peft==0.13.2.
请按任意键继续. . .

无言***

hypo3000 发表于 2025-11-6 21:55
:::::::::       ::::::::::       ::::::::::       :::::::::       ::::::::::           :::      ...

某些依赖自动更新了，需要对应更新peft>=0.17.0，如果你有动手能力，可以自行更新，否则只能等后期有时间，我再更新一版。