scribble-diffusion VS noya

Text to image with Scribble Diffusion

Eh, I don't think this is better than https://scribblediffusion.com/. None of the three images were at all like my drawing, but Scribble Diffusion did include the right elements in the right places.

Demo: Scribble Diffusion GitHub: Scribble Diffusion Repository

You can get several free acccess interactions with a version here ControlNet Scribble (ie if you keep using it for long enough/ several tries then it will ask you to set up an account) ...... this is the backend for a simpler browser interface at Scribble Diffusion but the ControlNet one above allows you to upload an image, so, yeah draw a scribble on a piece of paper, take a photo with your phone and then upload

I feel embarrassed to jump on the AI bandwagon, but have you tried uploading this into something like Scribble Diffusion?

ScribbleDiffusion: Turns scribbles with descriptions into really cool images.

scribblediffusion.com

Thanks so much! You should try it! In this case my drawing is more elaborate, but you will be surprised that the simplest drawing can achieve great results! If your drawing is not very good then the prompt is very important! Give it a try at https://scribblediffusion.com/ and let me know how it went!

Hi HN, we’re building Noya (https://noya.io), a product design tool that lets everyone design like a designer. Here’s a video: https://player.vimeo.com/video/797476910.

Getting from a product idea to a design is too hard. Wireframing tools (e.g. Balsamiq) are limited and their output is too low-fidelity to get people excited about the idea. On the other hand, high-fidelity design tools (e.g. Figma) require advanced skills and are better for tweaking fine details than hashing out a big picture. Meanwhile, companies have an insatiable need to make new screens and change existing ones, and hiring more designers is time-consuming and expensive.

David and I were on the design tools team at Airbnb when we realized there’s another solution: let designers encode their knowledge (e.g. design rules and components) into a tool, then let non-designers (PMs, marketing, engineers) use that tool to make new screens and features. This helps remove design as a bottleneck for a lot of product development. We built such tools at Airbnb, and with Noya we’re building them for product teams everywhere.

Current design tools are too freeform for non-designers to design great products. They let you do anything, like draw rectangles and move text blocks anywhere, so it's easy to mess things up, introduce inconsistencies, and so on. With Noya, designers set up "guardrails" in the form of a design system (rules and components for a company's design), then non-designers work within those constraints. This makes it harder to mess up and quicker to build something that fits in with your product. Footguns begone!

It all starts with wireframing, i.e. drawing a minimal layout that shows the elements that would exist on the screen. Noya combines wireframes and design systems to generate high-fidelity designs and code. If you have an idea for a user interface, you can use Noya to quickly wireframe that idea by clicking and dragging to place blocks for each element of your user interface. For each block, choose a type and provide any content that goes inside it.

Based on the rules and component library of the design system you select, Noya automatically turns your wireframe into a high-fidelity design. This design can be exported to design files, to Figma or Sketch, or to React code.

(If you’re curious what the React code looks like, try exporting and take a look! There’s plenty of room for improvement, especially around responsive layouts, but we think it’s a reasonable starting point. The code export is configurable on a per-design-system basis so that it’s closer to a company’s preferred standards).

Most tools in this space are optimized for either low-fidelity wireframes that are quick to create (e.g. Balsamiq), or high-fidelity output that’s slow to create (e.g. Figma). We think there’s a gap in the market for a great wireframing tool that produces a high-fidelity output quickly. For example, two-thirds of Figma users are non-designers. While there are many valid reasons for a non-designer to use Figma, there’s often a lot of upfront effort required to learn the tool and set up components. We think there should be a lower-effort way for non-designers to create high-fidelity designs.

Based on feedback from our Show HN (https://news.ycombinator.com/item?id=34848583), we’ve improved our onboarding, revamped our entire block library, and added a documentation reference for each block type. The docs are interactive, so you can play with our editor without signing up: https://noya.io/app/docs.

Startup founders and PMs have used Noya to build landing pages, dashboards, and other flows of their apps. We have some templates on our site (https://noya.io/templates) that give examples of what people commonly build in Noya. We use Noya ourselves, and have been surprised by how frustrating it was to go back to existing design tools after using even the earliest prototypes of Noya. Existing design tools just aren’t built for the comprehensive design systems that products are based on today.

The source code is available here (though largely undocumented & unlicensed): https://github.com/noya-app/noya. We’re not focused on growing our open source community or supporting other design tool builders just yet, so we haven’t published our packages (renderer, canvas, etc) to npm, but we’re planning to use the Apache V2 license. We make money by offering a paid subscription.

Noya currently supports one design system based on Chakra UI. We’re adding additional design systems soon, including Material Design, as well as the ability to import custom design systems. If your company has an open source design system and you’re interested in trying Noya with it, we may be able to integrate your design system for free. Get in touch if you’re interested - [email protected].

We’d love for you to try Noya and let us know what you think! It’s still very much an MVP and all kinds of feedback are welcome.

Noya – Write text, get design and code.

Hi HN. I've been working on a new browser-based design tool that's ready for you to try.

The idea is you work on your design in low fidelity wireframes, while still getting a high fidelity output that you can share or use as a reference for your implementation. The way it works is by mapping low fidelity blocks you draw into high fidelity design system & React components.

I spent several years working on design tools at companies like Airbnb, and I think the ideas behind many of the tools we built for designing at scale could really help startups and small teams as well. I would love any feedback you have!

PS: Most of Noya is open source at https://github.com/noya-app/noya

Hi HN! We’ve been building a new browser-based design tool that’s ready for you to play with!

My cofounder David and I were previously on the Design Tools team at Airbnb, where we built lots of innovative tools to improve the design process internally. Now we’re trying to bring this caliber of tools to everyone.

The first problem we’re trying to solve is the age-old problem of working in low fidelity vs. high fidelity when designing UI. Low fidelity wireframes are great for quick iteration while hashing out the main idea, while high fidelity mockups and prototypes are often better for conveying the idea to teammates or pitching the idea to customers.

With Noya, you get to work in low fidelity, while still getting a high fidelity output you can share. Noya does this by converting your low fidelity blocks into high fidelity design system & React components.

I think of the current version as an MVP still, since there’s a lot more that I want to add, but I’ve personally been finding it useful even with its limited feature set. I’d be very interested in any early feedback if you have a chance to play with it!

PS: We’ve open sourced most of Noya at https://github.com/noya-app/noya. Let us know if you’re interested in collaborating.