[Bug]: fatal: not a git repository (or any of the parent directories): .git

### Checklist - [ ] The issue exists after disabling all extensions - [ ] The issue exists on a clean installation of webui - [ ] The issue is caused by an extension, but I believe it is caused by a bug in the webui - [ ] The issue exists in the current version of the webui - [ ] The issue has not been reported before recently - [ ] The issue has been reported before but has not been fixed yet ### What happened? sometimes all LoRAs do not start, sometimes the console offers to close itself when trying to change the checkpoint - " To create a public link, set `share=True` in `launch()`. Startup time: 25.1s (prepare environment: 5.9s, import torch: 6.7s, import gradio: 0.6s, setup paths: 1.1s, initialize shared: 0.9s, other imports: 0.6s, load scripts: 3.5s, create ui: 5.0s, gradio launch: 0.7s). Unloading first loaded model: anyloracleanlinearmix_v10.safetensors [9807d1172b] Performing complete teardown of model: anyloracleanlinearmix_v10.safetensors [9807d1172b] Model teardown completed Current memory usage after unload: RSS=2.93 GB C:\Users\000\Desktop\stable-diffusion-webui-reForge- main\modules\sd_models.py:657: FutureWarning: `torch.distributed.reduce_op` is deprecated, please use `torch.distributed.ReduceOp` instead if (isinstance(obj, torch.Tensor) and Memory change: 0.11 MB (2.93 GB total) Loading model NoobAI-XL-v1.1.safetensors [6681e8e4b1] (1 of 1) Loading weights [6681e8e4b1] from C:\Users\000\Desktop\stable- diffusion-webui-reForge-main\models\Stable-diffusion\NoobAI-XL-v1.1.safetensors Skipping checkpoint CLIP loading - will use separate TE: TE: NoobAI-XL-v1.1 No checkpoint CLIP loaded - must use separate text encoder Loading separate text encoder: TE: NoobAI-XL-v1.1 Для продолжения нажмите любую клавишу . . . " and sometimes a completely normal image at an intermediate stage becomes a large artifact after generation ### Steps to reproduce the problem I installed it along with CLIP installation problems, thanks to the help. Tried to completely reinstall Git and Python, nothing helped ### What should have happened? --- ### What browsers do you use to access the UI ? Other ### Sysinfo I use Opera GX Palit 3080ti (12 GB), 32GB Ram, ryzen 9 5950x, and a secondary video card MSI GeForce GTX 1660 Gaming (6GB) ### Console logs ```Shell venv "C:\Users\000\Desktop\stable-diffusion-webui-reForge-main\venv\Scripts\Python.exe" fatal: not a git repository (or any of the parent directories): .git fatal: not a git repository (or any of the parent directories): .git Python 3.10.6 (tags/v3.10.6:9c7b4bd, Aug 1 2022, 21:53:49) [MSC v.1932 64 bit (AMD64)] Version: f1.0.0v2-v1.10.1RC-1.10.1 Commit hash: <none> Installing requirements Launching Web UI with arguments: Total VRAM 12288 MB, total RAM 32676 MB pytorch version: 2.9.0+cu128 Set vram state to: NORMAL_VRAM Device: cuda:0 NVIDIA GeForce RTX 3080 Ti : native Hint: your device supports --pin-shared-memory for speed improvements if having 16GB or more VRAM. It may cause issues with 12GB VRAM or less. Hint: your device supports --cuda-malloc for a bit less vram usage and small speed improvement Hint: your device supports --cuda-stream for potential speed improvements but it may cause issues on some GPUs that have 6-8GB VRAM or less. CUDA Stream Activated: False W0222 16:17:41.567902 8344 venv\Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs. Using pytorch attention ControlNet preprocessor location: C:\Users\000\Desktop\stable-diffusion-webui-reForge-main\models\ControlNetPreprocessor CHv1.8.13: Get Custom Model Folder Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu. Tag Autocomplete: Could not locate model-keyword extension, Lora trigger word completion will be limited to those added through the extra networks menu. [-] ADetailer initialized. version: 26.2.0, num models: 10 Forge: False, reForge: True C:\Users\000\Desktop\stable-diffusion-webui-reForge-main\modules\sd_models.py:657: FutureWarning: `torch.distributed.reduce_op` is deprecated, please use `torch.distributed.ReduceOp` instead if (isinstance(obj, torch.Tensor) and Memory change: 2.75 MB (0.97 GB total) Loading model anyloracleanlinearmix_v10.safetensors [9807d1172b] (1 of 1) Loading weights [9807d1172b] from C:\Users\000\Desktop\stable-diffusion-webui-reForge-main\models\Stable-diffusion\anyloracleanlinearmix_v10.safetensors CHv1.8.13: Set Proxy: LatentDiffusion: Running in eps-prediction mode DiffusionWrapper has 0.00 M params. Skipping checkpoint CLIP loading - will use separate TE: TE: anyloracleanlinearmix_v10 No checkpoint CLIP loaded - must use separate text encoder Loading separate text encoder: TE: anyloracleanlinearmix_v10 WARNING:root:Text encoder missing keys: ['clip_l.text_projection'] Loaded text encoder TE: anyloracleanlinearmix_v10 in 0.4s (load clip weights: 0.3s) Replacing text encoder with: TE: anyloracleanlinearmix_v10 Updated global TE state to: TE: anyloracleanlinearmix_v10 Skipping apply_text_encoder() - separate TE already loaded during model initialization Model anyloracleanlinearmix_v10.safetensors [9807d1172b] loaded in 2.8s (memory cleanup: 0.6s, forge load real models: 1.2s, load VAE: 0.3s, calculate empty prompt: 0.6s). Memory change: 1.15 MB (6.44 GB total) 2026-02-22 16:17:51,588 - ControlNet - INFO - ControlNet UI callback registered. Running on local URL: http://127.0.0.1:7861 To create a public link, set `share=True` in `launch()`. Startup time: 25.1s (prepare environment: 5.9s, import torch: 6.7s, import gradio: 0.6s, setup paths: 1.1s, initialize shared: 0.9s, other imports: 0.6s, load scripts: 3.5s, create ui: 5.0s, gradio launch: 0.7s). ``` ### Additional information _No response_