stabilityMatrix에서 comfyUI를 구동하면 이런 에러메시지가 뜨는데 뭐가 문제일까요? [자필]

animateDiff를 추가하려고 했는데, 하고 나서 구동하니까 연결된 모델이 하나라도 있어야 한다고 해서

검색해갖고  mm_sd_v15_v2.ckpt라는걸 넣어주었더니

그건 해결된 것 같은데 다시 이런 에러가 뜨면서 구동이 중단됩니다.

도와주세요...

완전 초보입니다 ㅠㅠ

*참고로요 stable diffusuin web ui는 돌리면 이런 에러가 뜨면서 마지막 생성 단계에서 이미지가 안 나옵니다.

NVIDIA driver was found. Automatically changed backend to 'cuda'. You can manually select which backend will be used through '--backend' argument.

fatal: No names found, cannot describe anything.

Python 3.10.11 (tags/v3.10.11:7d4cc5a, Apr  5 2023, 00:38:17) [MSC v.1929 64 bit (AMD64)]

Version: 1.6.1

Commit hash: 03eec1791be011e087985ae93c1f66315d5a250e

Launching Web UI with arguments: --medvram --medvram-sdxl --xformers --api --autolaunch --skip-python-version-check --no-half

WARNING:xformers:WARNING[XFORMERS]: xFormers can't load C++/CUDA extensions. xFormers was built for:

    PyTorch 2.0.1+cu118 with CUDA 1108 (you have 2.0.1+cpu)

    Python  3.10.11 (you have 3.10.11)

  Please reinstall xformers (see https://github.com/facebookresearch/xformers#installing-xformers)

  Memory-efficient attention, SwiGLU, sparse and more won't be available.

  Set XFORMERS_MORE_DETAILS=1 for more details

Warning: caught exception 'Torch not compiled with CUDA enabled', memory monitor disabled

Loading weights [6ce0161689] from C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\models\Stable-diffusion\v1-5-pruned-emaonly.safetensors

Creating model from config: C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\configs\v1-inference.yaml

Running on local URL:  http://127.0.0.1:7860

To create a public link, set `share=True` in `launch()`.

Startup time: 14.3s (prepare environment: 0.7s, import torch: 5.5s, import gradio: 2.0s, setup paths: 2.4s, initialize shared: 0.2s, other imports: 1.9s, setup codeformer: 0.1s, load scripts: 0.8s, create ui: 0.4s, gradio launch: 0.3s).

Applying attention optimization: InvokeAI... done.

Model loaded in 2.4s (load weights from disk: 0.5s, create model: 0.4s, apply weights to model: 1.4s).

100%|##########| 20/20 [03:28<00:00, 10.43s/it]

*** Error completing request

*** Arguments: ('task(6ycnc8z2mi0e12x)', 'cute cat', '', [], 20, 'DPM++ 2M Karras', 1, 1, 7, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 'Use same checkpoint', 'Use same sampler', '', '', [], <gradio.routes.Request object at 0x000001EE0C884CA0>, 0, False, '', 0.8, -1, False, -1, 0, 0, 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0, False) {}

    Traceback (most recent call last):

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\call_queue.py", line 57, in f

        res = list(func(*args, **kwargs))

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\call_queue.py", line 36, in f

        res = func(*args, **kwargs)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\txt2img.py", line 64, in txt2img

        processed = processing.process_images(p)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\processing.py", line 733, in process_images

        res = process_images_inner(p)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\processing.py", line 879, in process_images_inner

        x_samples_ddim = decode_latent_batch(p.sd_model, samples_ddim, target_device=devices.cpu, check_for_nans=True)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\processing.py", line 594, in decode_latent_batch

        sample = decode_first_stage(model, batch[i:i + 1])[0]

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\sd_samplers_common.py", line 76, in decode_first_stage

        return samples_to_images_tensor(x, approx_index, model)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\sd_samplers_common.py", line 58, in samples_to_images_tensor

        x_sample = model.decode_first_stage(sample.to(model.first_stage_model.dtype))

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 17, in <lambda>

        setattr(resolved_obj, func_path[-1], lambda *args, **kwargs: self(*args, **kwargs))

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\sd_hijack_utils.py", line 28, in __call__

        return self.__orig_func(*args, **kwargs)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context

        return func(*args, **kwargs)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\diffusion\ddpm.py", line 826, in decode_first_stage

        return self.first_stage_model.decode(z)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\modules\lowvram.py", line 71, in first_stage_model_decode_wrap

        return first_stage_model_decode(z)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\models\autoencoder.py", line 90, in decode

        dec = self.decoder(z)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl

        return forward_call(*args, **kwargs)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 631, in forward

        h = self.mid.attn_1(h)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl

        return forward_call(*args, **kwargs)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\repositories\stable-diffusion-stability-ai\ldm\modules\diffusionmodules\model.py", line 258, in forward

        out = xformers.ops.memory_efficient_attention(q, k, v, attn_bias=None, op=self.attention_op)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 192, in memory_efficient_attention

        return _memory_efficient_attention(

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 290, in _memory_efficient_attention

        return _memory_efficient_attention_forward(

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\__init__.py", line 306, in _memory_efficient_attention_forward

        op = _dispatch_fw(inp)

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 94, in _dispatch_fw

        return _run_priority_list(

      File "C:\Users\yejupa\AppData\Roaming\StabilityMatrix\Packages\stable-diffusion-webui-directml\venv\lib\site-packages\xformers\ops\fmha\dispatch.py", line 69, in _run_priority_list

        raise NotImplementedError(msg)

    NotImplementedError: No operator found for `memory_efficient_attention_forward` with inputs:

         query       : shape=(1, 4096, 1, 512) (torch.float32)

         key         : shape=(1, 4096, 1, 512) (torch.float32)

         value       : shape=(1, 4096, 1, 512) (torch.float32)

         attn_bias   : <class 'NoneType'>

         p           : 0.0

    `cutlassF` is not supported because:

        device=cpu (supported: {'cuda'})

        Operator wasn't built - see `python -m xformers.info` for more info

    `flshattF` is not supported because:

        device=cpu (supported: {'cuda'})

        dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})

        max(query.shape[-1] != value.shape[-1]) > 128

        Operator wasn't built - see `python -m xformers.info` for more info

    `tritonflashattF` is not supported because:

        device=cpu (supported: {'cuda'})

        dtype=torch.float32 (supported: {torch.bfloat16, torch.float16})

        max(query.shape[-1] != value.shape[-1]) > 128

        Operator wasn't built - see `python -m xformers.info` for more info

        triton is not available

    `smallkF` is not supported because:

        max(query.shape[-1] != value.shape[-1]) > 32

        Operator wasn't built - see `python -m xformers.info` for more info

        unsupported embed per head: 512

---

 

뭐가 문제인지 하나도 모르겠네요 ㅠㅠ