When I try to run your Colab (thanks for that by the way), I get an error and I can't generate. Google Colab AI says this: Please explain the error: TypeError: object of type 'int' has no len() Colab AI The error is caused by the following line of code:
timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps) The timesteps argument is expected to be a list of integers, but in this case it is a string. To fix this, you can convert the string to a list of integers using the ast.literal_eval() function. timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, ast.literal_eval(timesteps))
Again, thank you for the Collab. It's a really nice bonus.
When I try to run your Colab (thanks for that by the way), I get an error and I can't generate.
Google Colab AI says this:
Please explain the error:
TypeError: object of type 'int' has no len()
Colab AI
The error is caused by the following line of code:
timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, timesteps)
The timesteps argument is expected to be a list of integers, but in this case it is a string. To fix this, you can convert the string to a list of integers using the ast.literal_eval() function.
timesteps, num_inference_steps = retrieve_timesteps(self.scheduler, num_inference_steps, device, ast.literal_eval(timesteps))
Fixed
HI, the collab is not giving access. it says request access.
Please try now.
bro please create a video on how to install it locally, I have tried it is very complicated for me.
It is and requires a buffed-up GPU. There is an initial low GPU version, maybe I'll do a vid on that.
please do a short video on how we can run it locally please@@the-ai-art
the comparison you show is nice@@the-ai-art
nice to bad you cant access collab
Fixed. Please try again
@@the-ai-art thank you it works
Hey nice work! Just want to ask that are you interested in our new ai generation product? Maybe I can send you beta version to you~
Sure. Why not.