使用safetensor是不是会报错？

[14790897]

──────────────────── Traceback (most recent call last) ──────────────────────╮ │ /content/sd-scripts/train_network.py:873 in │ │ │ │ 870 │ args = parser.parse_args() │ │ 871 │ args = train_util.read_config_from_file(args, parser) │ │ 872 │ │ │ ❱ 873 │ train(args) │ │ 874 │ │ │ │ /content/sd-scripts/train_network.py:168 in train │ │ │ │ 165 │ weight_dtype, save_dtype = train_util.prepare_dtype(args) │ │ 166 │ │ │ 167 │ # モデルを読み込む │ │ ❱ 168 │ textencoder, vae, unet, = train_util.load_target_model(args, we │ │ 169 │ │ │ 170 │ # モデルに xformers とか memory efficient attention を組み込む │ │ 171 │ train_util.replace_unet_modules(unet, args.mem_eff_attn, args.xfor │ │ │ │ /content/sd-scripts/library/train_util.py:3149 in load_target_model │ │ │ │ 3146 │ │ if pi == accelerator.state.local_process_index: │ │ 3147 │ │ │ print(f"loading model for process {accelerator.state.loca │ │ 3148 │ │ │ │ │ ❱ 3149 │ │ │ text_encoder, vae, unet, load_stable_diffusionformat = │ │ 3150 │ │ │ │ args, weight_dtype, accelerator.device if args.lowram │ │ 3151 │ │ │ ) │ │ 3152 │ │ │ │ /content/sd-scripts/library/train_util.py:3115 in _load_target_model │ │ │ │ 3112 │ load_stable_diffusion_format = os.path.isfile(name_or_path) # de │ │ 3113 │ if load_stable_diffusion_format: │ │ 3114 │ │ print(f"load StableDiffusion checkpoint: {name_or_path}") │ │ ❱ 3115 │ │ text_encoder, vae, unet = model_util.load_models_fromstable │ │ 3116 │ else: │ │ 3117 │ │ # Diffusers model is loaded to CPU │ │ 3118 │ │ print(f"load Diffusers pretrained models: {name_or_path}") │ │ │ │ /content/sd-scripts/library/model_util.py:856 in │ │ load_models_from_stable_diffusion_checkpoint │ │ │ │ 853 │ │ 854 # TODO dtype指定の動作が怪しいので確認する text_encoderを指定形式で作 │ │ 855 def load_models_from_stable_diffusion_checkpoint(v2, ckptpath, devic │ │ ❱ 856 │ , state_dict = load_checkpoint_with_text_encoder_conversion(ckpt │ │ 857 │ │ │ 858 │ # Convert the UNet2DConditionModel model. │ │ 859 │ unet_config = create_unet_diffusers_config(v2, unet_use_linear_pr │ │ │ │ /content/sd-scripts/library/model_util.py:833 in │ │ load_checkpoint_with_text_encoder_conversion │ │ │ │ 830 │ │ checkpoint = None │ │ 831 │ │ state_dict = load_file(ckpt_path) # , device) # may causes e │ │ 832 │ else: │ │ ❱ 833 │ │ checkpoint = torch.load(ckpt_path, map_location=device) │ │ 834 │ │ if "state_dict" in checkpoint: │ │ 835 │ │ │ state_dict = checkpoint["state_dict"] │ │ 836 │ │ else: │ │ │ │ /usr/local/lib/python3.10/dist-packages/torch/serialization.py:815 in load │ │ │ │ 812 │ │ │ │ return _legacy_load(opened_file, map_location, _weigh │ │ 813 │ │ │ except RuntimeError as e: │ │ 814 │ │ │ │ raise pickle.UnpicklingError(UNSAFE_MESSAGE + str(e)) │ │ ❱ 815 │ │ return _legacy_load(opened_file, map_location, pickle_module, │ │ 816 │ │ 817 │ │ 818 # Register pickling support for layout instances such as │ │ │ │ /usr/local/lib/python3.10/dist-packages/torch/serialization.py:1033 in │ │ _legacy_load │ │ │ │ 1030 │ │ │ f"Received object of type \"{type(f)}\". Please update to │ │ 1031 │ │ │ "functionality.") │ │ 1032 │ │ │ ❱ 1033 │ magic_number = pickle_module.load(f, pickle_load_args) │ │ 1034 │ if magic_number != MAGIC_NUMBER: │ │ 1035 │ │ raise RuntimeError("Invalid magic number; corrupt file?") │ │ 1036 │ protocol_version = pickle_module.load(f, pickle_load_args) │ ╰──────────────────────────────────────────────────────────────────────────────╯ UnpicklingError: invalid load key, '^'. ╭───────────────────── Traceback (most recent call last) ──────────────────────╮ │ /usr/local/bin/accelerate:8 in │ │ │ │ 5 from accelerate.commands.accelerate_cli import main │ │ 6 if name == 'main': │ │ 7 │ sys.argv[0] = re.sub(r'(-script.pyw|.exe)?$', '', sys.argv[0]) │ │ ❱ 8 │ sys.exit(main()) │ │ 9 │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/accelerate_cli.p │ │ y:45 in main │ │ │ │ 42 │ │ exit(1) │ │ 43 │ │ │ 44 │ # Run │ │ ❱ 45 │ args.func(args) │ │ 46 │ │ 47 │ │ 48 if name == "main": │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:1104 │ │ in launch_command │ │ │ │ 1101 │ elif defaults is not None and defaults.compute_environment == Com │ │ 1102 │ │ sagemaker_launcher(defaults, args) │ │ 1103 │ else: │ │ ❱ 1104 │ │ simple_launcher(args) │ │ 1105 │ │ 1106 │ │ 1107 def main(): │ │ │ │ /usr/local/lib/python3.10/dist-packages/accelerate/commands/launch.py:567 in │ │ simple_launcher │ │ │ │ 564 │ process = subprocess.Popen(cmd, env=current_env) │ │ 565 │ process.wait() │ │ 566 │ if process.returncode != 0: │ │ ❱ 567 │ │ raise subprocess.CalledProcessError(returncode=process.return │ │ 568 │ │ 569 │ │ 570 def multi_gpu_launcher(args): │ ╰──────────────────────────────────────────────────────────────────────────────╯ CalledProcessError: Command '['/usr/bin/python3', 'train_network.py', '--config_file=config_file.toml', '--sample_prompts=sample_prompts.txt']' returned non-zero exit status 1.

[14790897]

cicitai下载的模型名字没自动修改，Length: 2400040320 (2.2G) [application/octet-stream] Saving to: ‘/content/Lora/sd_model/102222

[WSH032]

好的，我有空会看看。

所以现在问题是解决了吗？和之前的问题有点像 https://github.com/WSH032/kohya-config-webui/issues/4 ，应该确实是没改扩展名的问题。

是在用预设的模型，还是自定义的url下载？