Open lingtingfengyu opened 10 months ago
same error here linux w/installed n-driver 545.84 Launching Web UI with arguments: --xformers --listen --enable-insecure-extension-access (no --medvram needed w/3090) done >> pip install onnxruntime done >> pip install colored
No ONNX file found. Exporting ONNX... Traceback (most recent call last): File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/routes.py", line 422, in run_predict output = await app.get_blocks().process_api( File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1323, in process_api result = await self.call_function( File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/gradio/blocks.py", line 1051, in call_function prediction = await anyio.to_thread.run_sync( File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "/home/wrt/stable-diffusion-webui/venv/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 807, in run result = context.run(func, *args) File "/home/wrt/stable-diffusion-webui/extensions/Stable-Diffusion-WebUI-TensorRT/ui_trt.py", line 134, in export_unet_to_trt gr.Info("No ONNX file found. Exporting ONNX... Please check the progress in the terminal.") AttributeError: module 'gradio' has no attribute 'Info'
, after checked, Magic, gradio upgrade to gradio: 3.41.0 . IT WORKS NOW.
, after checked, Magic, gradio upgrade to gradio: 3.41.0 . IT WORKS NOW.
What do you mean by this I'm getting the same error? Do you mean you upgraded your Gradio?
yes after upgraded gradio, this issue gone
As you can see here I have Gradio 3.41.0 and still getting the same error. So maybe Morris did update something else without noticing. Let's try upgrading Python just in case x)
ok upgrading Python is already a headache, couldn't find the way. Why all the pain... lol
Have you installed these below before gradio
source ./venv/bin/activate pip install --upgrade pip pip install nvidia-cudnn-cu11==8.9.4.25 --no-cache-dir pip install --pre --extra-index-url https://pypi.nvidia.com/ tensorrt==9.0.1.post11.dev4 --no-cache-dir pip uninstall -y nvidia-cudnn-cu11 pip install onnxruntime pip install colored
I have exactly this problem. Exactly as @lingtingfengyu said.
I'm using the 1.6 stable release. And I think it's because it only supports version 1.5 and 2.1!
If it is other than this please let me know.
i havve RTX 2060 Card
How do I update Gradio? I have run the command as shown below and it appears to be working correctly. However, when I look at it on the web, it is still at 3.32 and has not been updated.
(venv) J:\sd150\stable-diffusion-webui>pip install --upgrade gradio ~~~~~ Installing collected packages: gradio Attempting uninstall: gradio Found existing installation: gradio 3.32.0 Uninstalling gradio-3.32.0: Successfully uninstalled gradio-3.32.0 Successfully uninstalled gradio-3.32.0 Successfully installed gradio-3.50.2
I was able to solve the above problem. In the end I could not figure out how to update gradio, but by upgrading stable diffusion to v1.6.0, gradio is now working as it is v3.41.0.
I was able to solve the above problem. In the end I could not figure out how to update gradio, but by upgrading stable diffusion to v1.6.0, gradio is now working as it is v3.41.0.
Are u sure ? I have SD 1.6 but it doesn't work. what should I do ?
Sorry, I may have misunderstood that SD itself is v1.6 and the version of Stable diffusion Web UI.
How to upgrade your gradio in webui a1111 just simplely modify file and restart webui again
Yes , my vesion is a1111==1.52 and gradio==3.41
Not working with gradio 3.41.2 But working with 3.41.0
I think...
the problem is the arg --medvram, remove it from webuser.bat and you can use rt profiles
the problem still cannot be solved by updating the gradio==3.41.0. what can i do?please help me,thank you very much
the problem still cannot be solved by updating the gradio==3.41.0. what can i do?please help me,thank you very much
i solve this problem by change the opset from 17 to 14
Have you installed these below before gradio
source ./venv/bin/activate pip install --upgrade pip pip install nvidia-cudnn-cu11==8.9.4.25 --no-cache-dir pip install --pre --extra-index-url https://pypi.nvidia.com/ tensorrt==9.0.1.post11.dev4 --no-cache-dir pip uninstall -y nvidia-cudnn-cu11 pip install onnxruntime pip install colored
I'm a bit confused with your syntax, are you on Linux ? I don't have a 'bin' folder, activate is in Scripts for me Another confusing thing, you first install nvidia-cudnn, then tensorrt, then you uninstall nvidia-cudnn that you just installed, I don't get it. Why ?
Had this issue, fixed it by removing all my cmd COMMANDLINE_ARGS Which were: --api --xformers
First of all, you have to use the 512X512 basic setup and run it once to get the ONNX file, then set up the specs you want.
{'sample': [(1, 4, 96, 96), (2, 4, 128, 192), (8, 4, 256, 256)], 'timesteps': [(1,), (2,), (8,)], 'encoder_hidden_states': [(1, 77, 2048), (2, 77, 2048), (8, 154, 2048)], 'y': [(1, 2816), (2, 2816), (8, 2816)]} No ONNX file found. Exporting ONNX... Disabling attention optimization ERROR:root: Traceback (most recent call last): File "D:\sd\sd-webui-aki-v4.5\extensions\Stable-Diffusion-WebUI-TensorRT\exporter.py", line 74, in export_onnx inputs = modelobj.get_sample_input( File "D:\sd\sd-webui-aki-v4.5\extensions\Stable-Diffusion-WebUI-TensorRT\models.py", line 1163, in get_sample_input latent_height, latent_width = self.check_dims( File "D:\sd\sd-webui-aki-v4.5\extensions\Stable-Diffusion-WebUI-TensorRT\models.py", line 269, in check_dims and latent_width <= self.max_latent_shape AssertionError
During handling of the above exception, another exception occurred:
Traceback (most recent call last): File "D:\sd-webui-aki-v4.4\python\lib\site-packages\gradio\routes.py", line 488, in run_predict output = await app.get_blocks().process_api( File "D:\sd-webui-aki-v4.4\python\lib\site-packages\gradio\blocks.py", line 1431, in process_api result = await self.call_function( File "D:\sd-webui-aki-v4.4\python\lib\site-packages\gradio\blocks.py", line 1103, in call_function prediction = await anyio.to_thread.run_sync( File "D:\sd-webui-aki-v4.4\python\lib\site-packages\anyio\to_thread.py", line 31, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "D:\sd-webui-aki-v4.4\python\lib\site-packages\anyio_backends_asyncio.py", line 937, in run_sync_in_worker_thread return await future File "D:\sd-webui-aki-v4.4\python\lib\site-packages\anyio_backends_asyncio.py", line 867, in run result = context.run(func, args) File "D:\sd-webui-aki-v4.4\python\lib\site-packages\gradio\utils.py", line 707, in wrapper response = f(args, **kwargs) File "D:\sd-webui-aki-v4.4\extensions\Stable-Diffusion-WebUI-TensorRT\ui_trt.py", line 135, in export_unet_to_trt export_onnx( File "D:\sd-webui-aki-v4.4\extensions\Stable-Diffusion-WebUI-TensorRT\exporter.py", line 129, in export_onnx exit() File "D:\sd-webui-aki-v4.4\python\lib_sitebuiltins.py", line 26, in call raise SystemExit(code) SystemExit: None