Kyle

> Thanks for reporting, looks like an upstream Jina issue, will transfer to Jina repo It was actually because I was not changing the name_docarray for each run as I...

I actually may try to get a fork working. I know TubroAnimation with an init video works and has a working notbook for Stable Diffusion but I would like to...

I will look at it in a couple hours. Those are errors I've solved so some fixes must have been missed making it in. But yes, please refer all issues...

Quick question, what location are you in when you run the command and what command are you running. If you navigate to /visualdiffusion/ and run ```python prdgui.py``` it won't function...

This is from an old version of the GUI, the current version has the symmloss scale fixed, and I just submitted a fix for the lack of a progress.png on...

I mean, it's certainly possible. The way the prompt is handled in the json, it's just another nested dictionary that can be indexed. So adjusting it's value isn't an issue,...

I can imagine a button to add "prompts" and a button to add new "prompt step". The first button increases amount of the currently displayed prompts, the second button adds...

Doing that would mess with the current multi-prompt with weights. The suggestion I made with the prompts and prompt steps would be completely modular.

 Well you got me started...

The way PRD handles these nested dictionaries, which contain lists at different levels of nesting, is driving me nuts. Making it work for both multiple prompts and multiple steps as...