seruva19 / kubin

Web-GUI for Kandinsky text-to-image diffusion models.
177 stars 18 forks source link

kd-animation error #150

Closed videoprice closed 1 year ago

videoprice commented 1 year ago

hi, have a error in kd-animation "No module named 'deforum_kandinsky'"

seruva19 commented 1 year ago

'deforum_kandinsky' is a folder from the root of original repo https://github.com/ai-forever/deforum-kandinsky and it is downloaded in runtime during installation of the 'kd-animation' extension. This error probably means that for whatever reasons the contents of the repo was not downloaded. What you can try is to clone or download the 'kandinsky-deforum' repo and just put folder 'deforum_kandinsky' from there to 'extensions/kd-animation' folder inside kubin root directory. And it should work.

videoprice commented 1 year ago

ok, but now have a second error: "error Model_Diffusers22' object has no attribute 'prepare_model"

thanks

seruva19 commented 1 year ago

Check the output of command git log --pretty=format:'%h' -n 1 launched from the application root. The result should be '0425422'. If it's not, then for some reasons your application is outdated and you have to update it using git pull or update script.

videoprice commented 1 year ago

thanks, update is done, but same error is still here

Traceback (most recent call last): File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\gradio\routes.py", line 442, in run_predict output = await app.get_blocks().process_api( File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\gradio\blocks.py", line 1392, in process_api result = await self.call_function( File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\gradio\blocks.py", line 1097, in call_function prediction = await anyio.to_thread.run_sync( File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\anyio\to_thread.py", line 33, in run_sync return await get_asynclib().run_sync_in_worker_thread( File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\anyio_backends_asyncio.py", line 877, in run_sync_in_worker_thread return await future File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\anyio_backends_asyncio.py", line 807, in run result = context.run(func, args) File "C:\Users\video\AppData\Roaming\Python\Python310\site-packages\gradio\utils.py", line 703, in wrapper response = f(args, *kwargs) File "W:\kubin\extensions/kd-animation/setup_ext.py", line 69, in fn=lambda params: create_deforum_animation( File "W:\kubin\extensions/kd-animation/setup_ext.py", line 117, in create_deforum_animation prior, decoder = kubin.model.prepare_model("img2img") AttributeError: 'Model_Diffusers22' object has no attribute 'prepare_model'

seruva19 commented 1 year ago

Can you try to do a fresh install (in some other folder)? I cannot understand the origin of this error.