Hacker News Reader

Comment by sophrocyne | Hacker News Reader

There are already a number of local, inference options that are (crucially) open-source, with more robust feature sets.

And if the defense here is "but Auto1111 and Comfy don't have as user-friendly a UI", that's also already covered. https://github.com/invoke-ai/InvokeAI

View on HN

I switched to InvokeAI and won't go back to basic a1111 webui. I like how everything is laid out, there are workflow features, you can easily recall all properties (prompt, model, lora, etc.) used to generate an image, things can be organized into boards, and all off the boards/images/metadata are stored in a very well-designed sqlite database that can be tapped into via DataGrip.

automatic1111: great for the fast implementation of the most recent generative features

comfyui: excellent for workflows and recalling the workflows, as they're saved into the resulting image metadata (i.e. sharing images, shares the image generation pipeline)

InvokeAI: Great UX and community, arguably were a bit behind in features as they were focused on making the UI work well. Now at the stage of bringing in the best features of competitors - Like you, I can easily recommend it above all other options.

> recalling the workflows, as they're saved into the resulting image metadata (i.e. sharing images, shares the image generation pipeline)

Doesn't a1111 already do this? Theres a PNG Info tab where you can drag and drop a PNG and it will pull all the prompt, inverse prompt, model, etc. And then a button to send it to the main generation tab. It doesn't automatically load the model, but that may be intentional because of how long it takes to change loaded models.

Comfy is node based. The saved metadata pulls up the full nodal workflow.

> Doesn't a1111 already do this?

Not that provides the same thing, no, largely because of fundamental design differences.

> Theres a PNG Info tab where you can drag and drop a PNG and it will pull all the prompt, inverse prompt, model, etc. And then a button to send it to the main generation tab.

A1111 by nature, has a bunch of disconnected operations in separate tabs and scripts. Even if the PNG captures all of a generation operation that would be executed by a single launch-button click, its not really equivalent to capturing a whole ComfyUI workflow, which can be the equivalent of a process which would be numerous different tasks in A1111 with manually shuttling data between tabs and scripts.

A1111 has a bunch of manual "send to X" buttons to do with the output of runs, so that they can be the input of another task, wherein in Comfy those operations are part of one workflow with a pipeline connecting the output of one to the input of another. And when saving generation data, those manual shuttle points in A1111 are barriers as to what is part of a single generation that can be saved.

Can you actually use those workflows in some sort of API from a script to automate it from lets say a python script. Played arround with comfy. Really nice, but i would like to automate it within my own environment.

Yeah, Invoke's nodes/workflows backend can be hit via the API. That's how the entire front-end UI (and workflow editor/IDE) are built.

I'm positive this can be done w/ Comfy too.

> Can you actually use those workflows in some sort of API from a script to automate it from lets say a python script.

Yes, you can, and the workflow JSON format has a reduced "API form" that discards visual/UI related information.

Also, if you are using Python, you could do your automation in Comfy (as custom nodes) instead of outside, too.

It's just missing too many features for me still, even though I like what it has better. I use things like segment-anything, customer upscalers, I prefer how inpainting is controlled in A1111 where you can say if you want whole image or mask area only, etc.

I've personally been using SD.Next, which is a fork of A1111 with support for the diffuser backend, a cleaned-up UI, and also sometimes has support for newer things before A1111, though not always. It's plugin compatible with A1111.

Also just Krita with the diffusion AI plugin: https://github.com/Acly/krita-ai-diffusion

Yeah "Run Stable Diffusion locally" is a weird pitch since that's already easy to do tbh.

No idea whether or not the UI is user-friendly, but the installation steps alone for InvokeAI are already a barrier for 99.9% of the world. Not to say Noiselith couldn't be open-source, but it's clearly offering something different from InvokeAI.

I can't even figure out how one would install Noiselith. It has some text that says "Download for free on your PC", but it's not a button or a link. Maybe they're doing some weirdly locked-down user-agent sniffing and refuse to allow me to even attempt to download any version on Linux?

InvokeAI is installed via a script, sure, but it's also just a few clicks: download, extract, double-click on a specific file, enjoy.

There are two giant download buttons on the Noiselith homepage. The mac button downloads a dmg and the windows button downloads an exe.

Yeah invokeAI is fantastic!

Reply on news.ycombinator.com