InternalMegaT

Traceback (most recent call last): File "/usr/local/lib/python3.8/dist-packages/gradio/routes.py", line 284, in run_predict output = await app.blocks.process_api( File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line 982, in process_api result = await self.call_function(fn_index, inputs, iterator) File "/usr/local/lib/python3.8/dist-packages/gradio/blocks.py", line...

I tested it with the original 2.1 768 model, and a custom one that I made. Didn't work showed same error. Same thing also goes for 2.0 model.

> You are running an old version of the colab, remove the folder sd and use the links from the main page of the repo This did not work

> I think I just trained a model with 2.1 on a 16BG GPU, don't know which though. Maybe you are on 12GB and are running out of memory? For...

> Also This is Fast Stable Diffusion not Fast Dream Booth

> the error means that you didn't choose the correct version of the model in the dropdown menu in the last cell I did that too. Gave me an error...

I found out how to fix it. Apparently I needed to remove all of the other models so it only uses the 2.1 768 model

I also had to rename the model to "model.ckpt"

> Hi, I have been training faces on Realistic Vision model for about a week and results were always good, but today something is wrong, it seems that after loading...

> Guys, what are your base models? With SD1.5, it probably still works correctly. With SD2.1 (512 or 768), it gets terrible results. Moreover, the larger the dataset size, the...