Getting the following error when trying to run the model:
Using seed: 45274
Prompt: a photo of a male holding a gun, island in background, 90s action movie style, cinematic, detailed background, extremely detailed face, realistic, real photo, high quality, high resolution
img2img mode
Input image size: 512x678
Input image size set to: 512x688
Downloading LoRA weights from - HF path: XLabs-AI/flux-RealismLora
Loading LoRA took: 0.42 seconds
Traceback (most recent call last):
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/cog/server/worker.py", line 349, in _predict
result = predict(*payload)
^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context
return func(args, **kwargs)
^^^^^^^^^^^^^^^^^^^^^
File "/src/predict.py", line 308, in predict
pipe = pipe.to("cuda")
^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 435, in to
module.to(device, dtype)
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1174, in to
return self._apply(convert)
^^^^^^^^^^^^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply
module._apply(fn)
[Previous line repeated 3 more times]
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 805, in _apply
param_applied = fn(param)
^^^^^^^^^
File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1167, in convert
raise NotImplementedError(
NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.
Getting the following error when trying to run the model:
Using seed: 45274 Prompt: a photo of a male holding a gun, island in background, 90s action movie style, cinematic, detailed background, extremely detailed face, realistic, real photo, high quality, high resolution img2img mode Input image size: 512x678 Input image size set to: 512x688 Downloading LoRA weights from - HF path: XLabs-AI/flux-RealismLora Loading LoRA took: 0.42 seconds Traceback (most recent call last): File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/cog/server/worker.py", line 349, in _predict result = predict(*payload) ^^^^^^^^^^^^^^^^^^ File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/utils/_contextlib.py", line 116, in decorate_context return func(args, **kwargs) ^^^^^^^^^^^^^^^^^^^^^ File "/src/predict.py", line 308, in predict pipe = pipe.to("cuda") ^^^^^^^^^^^^^^^ File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/diffusers/pipelines/pipeline_utils.py", line 435, in to module.to(device, dtype) File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1174, in to return self._apply(convert) ^^^^^^^^^^^^^^^^^^^^ File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply module._apply(fn) File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply module._apply(fn) File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 780, in _apply module._apply(fn) [Previous line repeated 3 more times] File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 805, in _apply param_applied = fn(param) ^^^^^^^^^ File "/root/.pyenv/versions/3.11.10/lib/python3.11/site-packages/torch/nn/modules/module.py", line 1167, in convert raise NotImplementedError( NotImplementedError: Cannot copy out of meta tensor; no data! Please use torch.nn.Module.to_empty() instead of torch.nn.Module.to() when moving module from meta to a different device.