AMD GPU Issues, Stability Matrix loads and then stops.

[imcano95]

Hello im having an issue with stabilityMatrix and generating images. the generation of the prompt starts, after a couple seconds the image generation stops.

Aorus 6900xt EGPU Ubuntu 22.04

the error i get

RuntimeError:` HIP error: the operation cannot be performed in the present state
HIP kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
For debugging consider passing HIP_LAUNCH_BLOCKING=1.
Compile with `TORCH_USE_HIP_DSA` to enable device-side assertions.

. . . The Graphics card is being recognized it seems like.

The AMD card is being recognized 
`Total time: 0.09 seconds
[Parameters] Adaptive CFG = 7
[Parameters] CLIP Skip = 2
[Parameters] Sharpness = 2
[Parameters] ControlNet Softness = 0.25
[Parameters] ADM Scale = 1.5 : 0.8 : 0.3
[Parameters] CFG = 4.0
[Parameters] Seed = 1006958236632410843
[Parameters] Sampler = dpmpp_2m_sde_gpu - karras
[Parameters] Steps = 30 - 15
[Fooocus] Initializing ...
[Fooocus] Loading models ...
Refiner unloaded.
[Fooocus] Processing prompts ...
[Fooocus] Preparing Fooocus text #1 ...
Traceback (most recent call last):
  File "/home/izz/Desktop/Data/Packages/Fooocus/modules/async_worker.py", line 998, in worker
    handler(task)
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/izz/Desktop/Data/Packages/Fooocus/modules/async_worker.py", line 535, in handler
    expansion = pipeline.final_expansion(t['task_prompt'], t['task_seed'])
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/izz/Desktop/Data/Packages/Fooocus/extras/expansion.py", line 120, in __call__
    features = self.model.generate(**tokenized_kwargs,
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context
    return func(*args, **kwargs)
  File "/home/izz/Desktop/Data/Packages/Fooocus/venv/lib/python3.10/site-packages/transformers/generation/utils.py", line 1319, in generate
    and torch.sum(inputs_tensor[:, -1] == generation_config.pad_token_id) > 0`

im not so tech savy when it comes to this but im trying my hardest to install this since its part of my work. is this even possible to get a AMD Gpu with ROCM to run Stable Diffusion image generation. i done it with the CPU but that takes too long.

if someone can help me ill even send bitcoin if i can get this to function.

[github-actions[bot]]

This issue is stale because it has been open 30 days with no activity. Remove the stale label or comment, else this will be closed in 5 days.

[github-actions[bot]]

This issue was closed because it has been stale for 5 days with no activity.