jadechip

I am experiencing the same issue, I've verified using the Chrome debugging tools that UIManager.dispatchViewManagerCommand is called successfully, but nothing happens regardless. Has there been any updates?

+1 I'm having all kinds of issues trying to run the deamon in a production k8 cluster. The above would be a good solution.

Got it, thank you! Will eagerly await the release of the training code :)

Have you tried using convert-hf-to-gguf.py?

Perhaps we can just add something like this: ``` chat = ChatOpenAI(model="gpt-3.5-turbo-1106").bind( response_format={"type": "json_object"} ) ``` Somewhere around [here](https://github.com/joaomdmoura/crewAI/blob/327d5c3a539778704f252461b55c114a8c3a716d/src/crewai/agent.py#L226).

@futurevessel thank you for your response. I'm trying to get the script to run but running into some errors: `!python ./convert_original_stable_diffusion_to_diffusers.py --checkpoint_path ./sd-vae-ft-mse-original/vae-ft-mse-840000-ema-pruned.ckpt --dump_path sd-v15-vae/` ``` 2023-01-29 14:22:40 (39.0 MB/s)...

I might be able to comment out the code not related to the VAE in the `./convert_original_stable_diffusion_to_diffusers.py `script 🤔

@futurevessel Yes, downloading the default VAE from [stabilityai/sd-vae-ft-mse](https://huggingface.co/stabilityai/sd-vae-ft-mse/tree/main) works as that repo has the VAE in ".bin" format. However in the [stabilityai/sd-vae-ft-mse-original](https://huggingface.co/stabilityai/sd-vae-ft-mse-original/tree/main) repo the VAE is stored as vae-ft-mse-840000-ema-pruned.ckpt and...

Here is the error: `Entry Not Found for url: https://huggingface.co/stabilityai/sd-vae-ft-mse-original/resolve/main/diffusion_pytorch_model.bin.`

@Zengyi-Qin Sounds good, will report back once I have proper training results.