qunash

[OOM] Memory blows out when trying to upscale images larger than 128x128 using StableDiffusionUpscalePipeline

12

### Describe the bug When trying to upscale images larger than 128x128 the progress goes to 100% and then crashes with CUDA OOM. With 512x512 images it's trying to allocate...

RuntimeError: Input type (c10::Half) and bias type (float) should be the same

5

First of all, congrats on the great work! I got this error in the middle of training on T4 in a colab: ``` ***** Running training ***** Num examples =...

Is it possible to resume training of a lora checkpoint?

6

I tried saving a pipeline patched with lora `.pt` checkpoint an then feeding it to the training script, but that errors out.

### Discussed in https://github.com/qunash/chatgpt-advanced/discussions/53 Originally posted by **guidevops** February 8, 2023 Dear WebChatGPT Team, I am a user of the WebChatGPT browser extension and I love the Prompt Editor feature....

### Feature Description I propose adding an `onAppend` callback function to the `useChatOptions`. This callback would be invoked whenever a user message is appended to the chat list using the...