Skip to main content

New top story on Hacker News: Show HN: Shortbread App – AI-powered, romantic comics for women

Show HN: Shortbread App – AI-powered, romantic comics for women
14 by Fengjiao | 8 comments on Hacker News.
Hi HN! Fengjiao and Evan here. We are building Shortbread App, Netflix for webcomics. We publish guilty-pleasure romance series (think 50 Shades of Gray) as comics. Like the mature version of Webtoon. You can see two comics episodes at https://ift.tt/fUV0Scs... https://ift.tt/PnT9wXS... , and read more in the app via https://ift.tt/PGrzN0o . All comics in the app are made by artists using the Shortbread AI Comics Studio ( https://shortbread.ai ). It is a powerful Photoshop-like editor that speeds up comic creation 10x with AI. The editor provides consistency and granular artistic control. More below. We first posted on HN 6 months ago when we built a prompt-to-comics AI ( https://ift.tt/KhCHoQc ). We sunsetted this soon after - it was a fun experiment but it didn’t meet the real need of comic artists. Shortbread Studio now changes this by enhancing how creators naturally work instead of replacing them. The tech: One-shot Character LoRA: Artists upload a single photo of their character. Our backend uses prompt engineering and ControlNet pipelines to generate a synthetic dataset from this photo. This dataset shows the character in all kinds of angles, poses and facial expressions that the artist can pick the best from. It’s then sent to our LoRA training service to create a LoRA model. This takes about 7 minutes. Control -> Redraw -> Refine Workflow: In real life drawing, you draw, erase, and draw again. The human creative process is iterative. In Shortbread Studio, artists can start from a text prompt, a sketch, a web image or a pose reference as a basis, create an initial panel and quickly modify and regenerate until they get what they want. If you spend 5 seconds, you get a decent panel. If you spend 10 minutes, you can push the limits and get pro results. Built-in Post-Processing: The editor’s features include liquify, upscale, remove background, and outpainting to extend an image. This allows artists to remove, add, or modify parts of an image on a pixel level without drawing by hand. We combine this with segmentation models like Segment Anything ( https://ift.tt/8yboBLw ) to support intelligently selecting and editing a part of an image. Google-docs like collaboration: The Studio runs in the browser and supports comments and collaboration. LLM Powered Copy Editor: Comics need text. An AI agent proofreads speech bubbles, fixes lettering and identifies grammar mistakes. Read our comics: https://ift.tt/mDESR7e (free to download + read, iOS + Android) All of the above are built by a team of 3 engineers including myself. I will be around to answer any questions in this thread!

Comments

Popular posts from this blog

New top story on Hacker News: Ask HN: Is the EULA on my new $30k RED cinema camera legal?

Ask HN: Is the EULA on my new $30k RED cinema camera legal? 70 by red_throwaway | 77 comments on Hacker News. TLDR: I bought a $30K professional cinema camera that doesn't work unless I sign away my rights to privacy and possibly the video content I make with it ( at least it seems ) Over the past few years my photography business has seen a surge in demand for ultra high quality video production work. In an effort to meet this demand, I picked up one of RED Digital Cinema's newest pro camera bodies, the RED V-RAPTOR. Considering this camera is used by professional filmmakers to create films destined for cinemas, it's not surprising that it came with a $30k price tag. After unboxing and assembling it, I power the camera on and the first thing I see is a wall of legal text on the embedded LCD. Turns out it's a "Software License Agreement" that I'm required to consent to using the on-camera menu buttons before any of the camera's functionality becomes

New top story on Hacker News: Show HN: Eva AI-Relational Database System for Faster AI-Powered Applications

Show HN: Eva AI-Relational Database System for Faster AI-Powered Applications 28 by jarulraj | 0 comments on Hacker News. Hi friends, We are building EVA, an AI-Relational database system with first-class support for deep learning models. Our goal with EVA is to create a platform that supports AI-powered multi-modal database applications operating on structured (tables, feature vectors, etc.) and unstructured data (videos, podcasts, pdf, etc.) with deep learning models. EVA comes with a wide range of models for analyzing unstructured data, including models for object detection, OCR, text summarization, audio speech recognition, and more. The key feature of EVA is its AI-centric query optimizer. This optimizer is designed to speed up AI-powered applications using a collection of optimizations inspired by relational database systems. Two of the most important optimizations are: + Caching: EVA automatically reuses previous query results (e.g., inference results), eliminating redundant