RTX 5090 with 32g VRAM failed to generate Panorama Image #29
Description
(matrix3d) root@autodl-container-65f24387ad-142143b0:~/autodl-tmp/Matrix-3D# python code/panoramic_image_generation.py \
--mode=t2p \ --prompt="a medieval village, half-timbered houses, cobblestone streets, lush greenery, clear blue sky, detailed textures, vibrant colors, high resolution" \ --output_path="./output/example1"
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 3/3 [00:00<00:00, 48.86it/s]
Loading pipeline components...: 14%|████████████████ | 1/7 [00:00<00:00, 6.28it/s]You set add_prefix_space. The tokenizer needs to be converted from the slow tokenizers
Loading pipeline components...: 29%|████████████████████████████████ | 2/7 [00:00<00:00, 5.58it/s]torch_dtype is deprecated! Use dtype instead!
Loading checkpoint shards: 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 2/2 [00:00<00:00, 95.76it/s]
Loading pipeline components...: 100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 7/7 [00:00<00:00, 13.24it/s]
Traceback (most recent call last):
File "/root/autodl-tmp/Matrix-3D/code/panoramic_image_generation.py", line 118, in
main(args)
File "/root/autodl-tmp/Matrix-3D/code/panoramic_image_generation.py", line 48, in main
).to(device)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/diffusers/pipelines/pipeline_utils.py", line 541, in to
module.to(device, dtype)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/diffusers/models/modeling_utils.py", line 1383, in to
return super().to(*args, **kwargs)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1369, in to
return self._apply(convert)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 928, in _apply
module._apply(fn)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 928, in _apply
module._apply(fn)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 928, in _apply
module._apply(fn)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 955, in _apply
param_applied = fn(param)
File "/root/autodl-tmp/envs/matrix3d/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1355, in convert
return t.to(
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 90.00 MiB. GPU 0 has a total capacity of 31.36 GiB of which 21.06 MiB is free. Including non-PyTorch memory, this process has 31.33 GiB memory in use. Of the allocated memory 30.84 GiB is allocated by PyTorch, and 6.07 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/notes/cuda.html#environment-variables)