有冇人識stable diffusion幫下我

睇youtube教 係extensions裝野之後就輕左

*** Error completing request
*** Arguments: ('task(e1ye16hk7knlps8)', '', '', [], 20, 0, False, False, 1, 1, 7, -1.0, -1.0, 0, 0, 0, False, 512, 512, False, 0.7, 2, 'Latent', 0, 0, 0, 0, '', '', [], <gradio.routes.Request object at 0x0000022D48E2BBB0>, 0, False, False, 'positive', 'comma', 0, False, False, '', 1, '', [], 0, '', [], 0, '', [], True, False, False, False, 0) {}
Traceback (most recent call last):
File "Q:\stablediffusion\stable-diffusion-webui\modules\call_queue.py", line 58, in f
res = list(func(*args, **kwargs))
File "Q:\stablediffusion\stable-diffusion-webui\modules\call_queue.py", line 37, in f
res = func(*args, **kwargs)
File "Q:\stablediffusion\stable-diffusion-webui\modules\txt2img.py", line 62, in txt2img
processed = processing.process_images(p)
File "Q:\stablediffusion\stable-diffusion-webui\modules\processing.py", line 677, in process_images
res = process_images_inner(p)
File "Q:\stablediffusion\stable-diffusion-webui\modules\processing.py", line 794, in process_images_inner
samples_ddim = p.sample(conditioning=p.c, unconditional_conditioning=p.uc, seeds=p.seeds, subseeds=p.subseeds, subseed_strength=p.subseed_strength, prompts=p.prompts)
File "Q:\stablediffusion\stable-diffusion-webui\modules\processing.py", line 1054, in sample
samples = self.sampler.sample(self, x, conditioning, unconditional_conditioning, image_conditioning=self.txt2img_image_conditioning(x))
File "Q:\stablediffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 464, in sample
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "Q:\stablediffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 303, in launch_sampling
return func()
File "Q:\stablediffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 464, in <lambda>
samples = self.launch_sampling(steps, lambda: self.func(self.model_wrap_cfg, x, extra_args={
File "Q:\stablediffusion\stable-diffusion-webui\venv\lib\site-packages\torch\utils\_contextlib.py", line 115, in decorate_context
return func(*args, **kwargs)
File "Q:\stablediffusion\stable-diffusion-webui\repositories\k-diffusion\k_diffusion\sampling.py", line 145, in sample_euler_ancestral
denoised = model(x, sigmas[i] * s_in, **extra_args)
File "Q:\stablediffusion\stable-diffusion-webui\venv\lib\site-packages\torch\nn\modules\module.py", line 1501, in _call_impl
return forward_call(*args, **kwargs)
File "Q:\stablediffusion\stable-diffusion-webui\modules\sd_samplers_kdiffusion.py", line 215, in forward
devices.test_for_nans(x_out, "unet")
File "Q:\stablediffusion\stable-diffusion-webui\modules\devices.py", line 155, in test_for_nans
raise NansException(message)
modules.devices.NansException: A tensor with all NaNs was produced in Unet. This could be either because there's not enough precision to represent the picture, or because your video card does not support half type. Try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion or using the --no-half commandline argument to fix this. Use --disable-nan-check commandline argument to disable this check.


救下我

It appears you're encountering a NansException error in your Python program which is working with a machine learning model for image generation. The error message provides some helpful information on possible causes and solutions:

Cause: The error could be due to insufficient precision to represent the picture or your video card not supporting the half data type.
Solutions:
You could try setting the "Upcast cross attention layer to float32" option in Settings > Stable Diffusion.
You could use the --no-half command-line argument.
If you want to disable the NaN check, you can use the --disable-nan-check command-line argument.
Here is how you might adjust your command line arguments:

bash
Copy
python your_script.py --no-half --disable-nan-check
Please replace your_script.py with the actual name of your Python script.

Remember, these solutions are based on the error message provided. If the error persists after trying these solutions, you should consider debugging your script further. It might be helpful to look at the inputs to your model when the error occurs to see if they are causing the issue.

舊卡 A記 I記卡 未必support fp16,
sd要用no half 個d cmd args 黎開

點幫你啊大佬