Closed kingmateo closed 1 year ago
read last ling of logs
this is a problem. im encountering it on my gtx 1650 aswell. using arch linux
that is to be expected on 1650 --lowvram --precision full --no-half --xformers --medvram is possible but if you want to generate any larger than 512x512 you have to use --lowvram
failed to install? then nuke the install, get the new version of web ui
i have a 3060ti, 32gb of ram and a i7-10700KF and it gives this error thingie
hi guys pls help me i get an error when i click on interrogate clip *** Error interrogating Traceback (most recent call last): File "C:\Users\A\Desktop\A1111\modules\interrogate.py", line 193, in interrogate self.load() File "C:\Users\A\Desktop\A1111\modules\interrogate.py", line 121, in load self.blip_model = self.load_blip_model() File "C:\Users\A\Desktop\A1111\modules\interrogate.py", line 101, in load_blip_model blip_model = models.blip.blip_decoder(pretrained=files[0], image_size=blip_image_eval_size, vit='base', med_config=os.path.join(paths.paths["BLIP"], "configs", "med_config.json")) IndexError: list index out of range
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. how to fix
Is there an existing issue for this?
What happened?
It was working properly. Suddenly he encountered a problem and gave the following message:
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. Time taken: 8.75sTorch active/reserved: 2346/2406 MiB, Sys VRAM: 4054/4096 MiB (98.97%)
system profile: Processor : i5-9400F RAM : 16 GB VGA : GTX 1650 SUPER
Steps to reproduce the problem
What should have happened?
I don't know, I just know that everything was working fine and suddenly everything went wrong
Commit where the problem happens
Latest version (python: 3.10.6 • torch: 1.13.1+cu117 • xformers: N/A • gradio: 3.28.1 • commit: 5ab7f213 • checkpoint: 7fb0fb0b10)
What platforms do you use to access the UI ?
Windows
What browsers do you use to access the UI ?
Google Chrome
Command Line Arguments
List of extensions
animator_extension canvas-zoom CFG-Schedule-for-Automatic1111-SD ebsynth_utility sd_save_intermediate_images sd-webui-3d-open-pose-editor sd-webui-additional-networks sd-webui-controlnet sd-webui-deforum sd-webui-lora-block-weight sd-webui-supermerger sd-webui-text2video stable-diffusion-webui-composable-lora stable-diffusion-webui-depthmap-script training-picker video_loopback_for_webui
Console logs
Additional information
I even enabled the Upcast cross attention layer to float32 option
I just failed to install Xform