j0yk1ll

> I've experimented with various projection architectures (perceiver-resampler, MAP, C-Abstractor). C-Abstractor worked best, but even it comes with the trade-off of 2-5% drop on the benchmarks we're measuring. It is...

> I am new to this library and thought that I just can't find this feature, but it looks like it is missing. So +1 for colored text input. Hey,...

> Excuse me, did the author use 768x1024 for training? Isn't sd1.5 for 512 resolution? Can 768x1024 be input? Please help me. @puduliu The example images in https://github.com/levihsu/OOTDiffusion/tree/main/run/examples are all...

> @j0yk1ll Hmm, I don't have a specific answer for the `ACCESS_TOKEN_SCOPE_INSUFFICIENT` error, but is it the same error reported [here](https://www.googlecloudcommunity.com/gc/AI-ML/Trying-to-use-gemini-using-google-generativeai-but-its-showing/m-p/692488)? Yes that's the error. I also couldn't find an...

+1

@jersobh From experience the agents are not good at respecting the order of actions that depend on each other, e.g. OpenGoogleSpreadsheetAction before InsertValueAction Did you test the implementation on some...

Here's another example of some endless loop INFO [agent] 🚀 Starting task: Visit the United Nations Country Fact Sheets and search for Brazil INFO [agent] 📍 Step 1 INFO [agent]...

> > ValueError: invalid literal for int() with base 10: 'generateContent > > can you share the stacktrace for this error? not sure i follow ``` POST Request Sent from...