jrmylee

We're currently working on our license/terms of service. Will have an answer for you shortly

yes definitely - thanks for the comments. We'll think about these points and get back to you later this week(via your contact in your bio)

Thanks this is very helpful

This is a work-in-progress, will get back you

To be very clear, I never said open-source is a problem.

In fact, Rubbrband started as an open-source project.

Each member of our team are ML researchers who have committed tens of thousands of lines to open-source.

I think you're conflating open-source with local installations. Our founding team was not fan of the interfaces that a lot of these projects have for our use cases. Not to mention, our hardware just doesn't run them.

Thanks Ed! really appreciate the feedback and support.

this is true. However I would my friends and I only have Macbooks so for us we wanted something that ran on the cloud

looking into this! thanks

yeah we went through a few pivots actually - Rubbrband was initially a mobile app for musicians. It would listen to your practice sessions and give feedback. We pivoted out of this primarily because of issues with the technology and market.

> So you are just telling us you are infringing on copyrights because nobody else does?

could you elaborate on this?

We don't offer any non-free-to-use checkpoints/LORAs on the platform out-of-the-box. If you wanted to import a model/lora to your own account from a CivitAI link you can do so, but we're at this point letting users do this under good faith that they have permission to use these models.

We also have face IP-adapter nodes in our app!

I would say there are a lot of more minor UX differences about our app than other offerings. One particular favorite of mine is the ability to switch between the Node Editor screen and the Playground screen using cmd+p.

We built this feature mainly bc the node editor isn't great for generating images, but it's awesome for dialing in the exact aesthetic you want with different nodes/settings. We built the Playground screen for generating images once you have a workflow you like.

appreciate it! would love to hear your thoughts after using it

gotcha thanks. any suggestions there? our goal is to have more levers than something like Midjourney, but without the complexity of comfy. Hard to convey this in a tagline lol

thanks! We're getting a ton of traffic right now and having some issues scaling... looking into this

this looks amazing. Particularly hopeful/interested if this could be used for wildfire prevention. Great work!

appreciate it :)

There's a few companies that provide APIs for image-gen. Personally I've been using the Kandinsky model off Replicate. It's really high quality, I'd recommend it: https://replicate.com/ai-forever/kandinsky-2.2

thanks, good luck with your startup as well!

haha I thought this was a funny example to use. On second thought we'll replace it with something better!

Yeah it's a great q

The way we think about it is that we're building a product for organizations in scaling mode, and they have deep needs on the product-side. Flexibility on filtering, different client-libraries, a clean observability interface, etc...

It's possible that we open-source parts of our models, but fundamentally we think we can capture value by building a great all-around web product, and not just a set of eval models.

actually very cool to me that you remember these pivots. From the inside these pivots were about solving problems we faced with our previous idea.

We mainly pivoted either because we discovered the market wasn't great, or we didn't have founder-market fit with the idea. There's a gut feeling aspect that plays in there as well, but it's mostly been analytical approach.

It's something we think about for sure

We think that image-gen models are lagging behind LLMs by about a year, so the problems that these models will have should look quite different in the future.

It'll require us to be adaptable and also to take chances on solving problems that aren't huge issues just yet, but are likely to be once models improve.

The short answer to this is to build evaluators for imperfections that our customers see as most pressing.

We have to balance that with our view of what we think will still be a problem in the future, as image generation models get better.

Eventually we want to build a vision model that's great at fine-grained details of images, while will take some time.

Thanks will fix this

A healthy mix of both at this point, I would say this problem is more of a problem of enterprise since it occurs at scale.

Yeah I think it's a great idea! Right now because the models are so finnicky changing the seed often does lead to an image with desirable qualities(ie: good hands) so this makes sense.

I do think over time the feedback loops will look much different, as the models get more solid.

Hm that's true.

We're working on ways to evaluate if an image looks "off" - but its a hard problem because a lot of it is subjective

Yes it is. That caption is indeed confusing - pushed a fix!