gradio VS stable-diffusion

There's also that library all the AI models started using that gives you a public URL to share. After researching it: https://www.gradio.app/ is the link.

It's used specifically for making simple UIs for machine learning apps. But I guess technically you could use it for anything.

What is the business model for https://www.taipy.io/, https://streamlit.io/, or https://www.gradio.app/? These are nice tools - but how will the sponsoring businesses support themselves? I didn't see any mention of enterprise plans, etc. Is the answer simply that "we've not announced our revenue model yet"? What should one expect?

Repo : https://github.com/gradio-app/gradio

There's TensorFlow.js for running machine learning on JavaScript, but personally, I'd prefer using the Python Gradio package, which is designed for creating UIs for machine learning inference demos.

I found an issue on gradio github but looks like it's closed so I am not sure if it's still a common issue or only I am facing it due to certain settings/absence of a fix. ( https://github.com/gradio-app/gradio/issues/3060 )

I disagree hard with this – for instance I've recently needed to dig into the code for the Gradio library, and when PRs are like https://github.com/gradio-app/gradio/pull/3300 (and the merge commit's message is what it is) it's hard to understand why some decisions have been made when doing `git annotate` later on.

Gradio for a ui that your commanderGPT can visit and use

gradio is documented, it doesn't seem very complex, it would be something like moving this block under the other one. i think it's ui_extra_networks.py, the file you are looking to edit. (if you do it make a copy to restore when you go to update)

Gradio did have an issue for a while where your URL was guessable, so unless you had a password it was pretty easy to find, but as far as I know they've increased the complexity so much that it's no longer an issue.

My script wouldn't work on the langchain because it was literally made within the gradio "docs builder" script that afaik was made specifically for their website (repo)

Which is a 1-click install of Stable Diffusion with an alternative web interface. You can choose a different approach but this one is pretty simple and I am new to this stuff.

an invisible watermarking of the outputs, to help viewers identify the images as machine-generated.

It sounds like you just want to set up Stable Diffusion to run locally. I don't think your computer's specs will be able to do it. You need a graphics card with a decent amount of VRAM. Stable diffusion is in Python as is almost every AI open source project I've seen. If you can get your hands on a system with an Nvidia RTX card with as much VRAM as possible, you're in business. I have an RTX 3060 with 12 gigs of VRAM and I can run stable diffusion and a whole variety of open source LLMs as well as other projects like face swap, Roop, tortoise TTS, sadtalker, etc...

Use specific GPU on multi GPU systems · Issue #87 · CompVis/stable-diffusion · GitHub

I dealt with this in one of my posts. At least SD 1.1 till 1.5 are all trained on a batch size of 2048. The version pretty much everyone uses (1.5) is first pretrained at a resolution of 256x256 for 237K steps on laion2B-en, at the end of those training steps it will have seen roughly 500M images in laion2B-en. After that it is pre-trained for 194K steps on laion-high-resolution at a resolution of 512x512, which is a subset of 170M images from laion5B. Finally it is trained for 1.110K steps on LAION aesthetic v2 5+. This is easily verified by taking a glance at the model card of SD 1.5. Though that one doesn't specify for part of the training exactly which aesthetic set was used for part of the training, for that you have to look at the CompVis github repo. Thus at the end of it all both the most recent images and the majority of images will have come from LAION aesthetic v2 5+ (seeing every image approx 4 times). Realistically a lot of the weights obtained from pretraining on 2B will have been lost, and only provided a good starting point for the weights.

stable diffusion · CompVis/stable-diffusion@2ff270f · GitHub

Here for example --> https://github.com/CompVis/stable-diffusion