sxela patreon

Stable WarpFusion v0.29 - QoL fixes, wav2lip, FaceFusion installers

🕑 Added 2023-12-23 14:42:51 +0000 UTC

Comments

Warpfusion

restart and run all

Kamil

Sorry not that one, but this one with cuda: RuntimeError Traceback (most recent call last) Cell In[58], line 865 863 thread_pool.join() 864 gc.collect() --> 865 torch.cuda.empty_cache() 866 executed_cells[cell_name] = True File D:\WarpFusion\WarpFusion\env\lib\site-packages\torch\cuda\memory.py:133, in empty_cache() 122 r"""Releases all unoccupied cached memory currently held by the caching 123 allocator so that those can be used in other GPU application and visible in 124 `nvidia-smi`. (...) 130 more details about GPU memory management. 131 """ 132 if is_initialized(): --> 133 torch._C._cuda_emptyCache() RuntimeError: CUDA error: device-side assert triggered CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect. For debugging consider passing CUDA_LAUNCH_BLOCKING=1. Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.

Kamil

Hi, I can work with the 1.5 model, but after switching to XL, there are errors. Can you try to help me with this?" DO THE RUN: NameError Traceback (most recent call last) Cell In[27], line 78 77 try: ---> 78 batchNum 79 except: NameError: name 'batchNum' is not defined During handling of the above exception, another exception occurred: ValueError Traceback (most recent call last) Cell In[27], line 82 80 renders = glob(f"{batchFolder}/*00.png") 81 renders_s = sorted([int(o.split('(')[-1].split(')')[0]) for o in renders]) ---> 82 batchNum = max(renders_s) 83 # batchNum = len(glob(f"{settings_out}/{batch_name}(*)_settings.txt"))-1 84 85 else: 86 batchNum = int(run_to_resume) ValueError: max() arg is an empty sequence