Hacker News with Generative AI: Image Generation

Stable Diffusion Comparison in C, Rust and Ruby (leetarxiv.substack.com)
Every blog, and every tutorial on Stable Diffusion (and diffusion models in general) is written in Python, or incoherent math symbols.
Stable Diffusion, Programming Languages, Image Generation, Performance Comparison
6 points by muragekibicho 10 days ago | 0 comments
Show HN: I built an AI image generator lets you create styled images in seconds (4oimage.site)
4oimage makes AI generation simple and fun. Create high-quality original images with just one click, choose from multiple artistic styles, and craft amazing visual works without any specialized skills.
AI, Image Generation, Tools, Creative Projects
5 points by bingbing123 12 days ago | 1 comments
Visual Reasoning Is Coming Soon (arcturus-labs.com)
I gotta say – I love it living in exponential times. I can just wish that something existed and then within a month it does! This time it happened with OpenAI's 4o image generation release. In this blog post I'll briefly cover the release and why I think it's pretty cool. Then I'll dive into a new opportunity that I think is even more exciting – visual reasoning.
Generative AI, Artificial Intelligence, Image Generation
122 points by softwaredoug 17 days ago | 44 comments
This Bench Does Not Exist (openbenches.org)
A StyleGAN3 generated image based on 25,000 photos from OpenBenches.
Artificial Intelligence, Image Generation, Creative Projects, Data Visualization
8 points by thinkingemote 18 days ago | 6 comments
No elephants: Breakthroughs in image generation (oneusefulthing.org)
Over the past two weeks, first Google and then OpenAI rolled out their multimodal image generation abilities. This is a big deal.
Generative AI, Image Generation, Artificial Intelligence, Computer Vision
445 points by Kerrick 21 days ago | 364 comments
Mirrors: The Blind Spot of Image and Video Generation Models (medium.com)
Recent advances in image generation models have demonstrated remarkable capabilities in creating photorealistic and imaginative visuals. However, a persistent challenge remains: accurately rendering reflections in mirrors.
Generative AI, Computer Vision, Image Generation, Artificial Intelligence
14 points by yamrzou 25 days ago | 3 comments
OpenAI just made it harder to turn your pics into Studio Ghibli-style images (aol.com)
OpenAI has blocked some users' requests for Studio Ghibli-style images.
OpenAI, Artificial Intelligence, Image Generation, Studio Ghibli
5 points by g42gregory 29 days ago | 0 comments
Vibe marketing prompts for OpenAI's new model (indiehackers.com)
OpenAI just launched a powerful new image generation model.
Marketing, Artificial Intelligence, Image Generation
19 points by ChanningAllen 30 days ago | 11 comments
Show HN: Fingernotes – handwritten notes which become their own preview image (fingernotes.com)
Show HN, Handwritten Notes, Image Generation
67 points by sumolessons 34 days ago | 20 comments
Experiment with Gemini 2.0 Flash native image generation (googleblog.com)
In December we first introduced native image output in Gemini 2.0 Flash to trusted testers. Today, we're making it available for developer experimentation across all regions currently supported by Google AI Studio.
Generative AI, Google, Image Generation
101 points by meetpateltech 45 days ago | 12 comments
InstantStyle: Free Lunch Towards Style-Preserving in Text-to-Image Generation (github.com/instantX-research)
InstantStyle is a general framework that employs two straightforward yet potent techniques for achieving an effective disentanglement of style and content from reference images.
Generative AI, Computer Vision, Machine Learning, Image Generation, Deep Learning
49 points by klaussilveira 50 days ago | 11 comments
Biases in Apple's Image Playground (giete.ma)
Although Image Playground is heavily restricted, and we do not have direct access to the underlying model, can we still use the prompting interface with the above image input to influence the skin tone of the resulting image? Turns out we can, and in precisely the biased way most image models behave 🤦‍♂️.
AI, Image Generation, Bias, Apple, Computer Vision
43 points by orf 68 days ago | 19 comments
Show HN: Generate Notion-style line avatars using AI (open source) (lineavatars.com)
Upload or capture a photo of your face, preferably at a slight angle. Then we’ll use AI to generate a line avatar for you. For free!
Artificial Intelligence, Open Source, Image Generation, Avatars
16 points by gregives 74 days ago | 6 comments
Visuali.io – A cross platform online infinite canvas AI image sandbox (visuali.io)
Turn your imagination into reality with Visuali's AI-powered generative art tools
Generative AI, AI Art, Image Generation, Online Tools
7 points by visuali 80 days ago | 2 comments
How to Train an AI Image Model on Yourself (coryzue.com)
Yesterday I had a couple hours to kill and decided to try out a project I’ve been meaning to explore for a long time: training my own AI image model so I can generate pictures of myself that look like this:
Generative AI, Artificial Intelligence, Image Generation, Machine Learning
207 points by aberoham 84 days ago | 42 comments
TokenVerse: Multi-Concept Personalization in Token Modulation Space by Google (token-verse.github.io)
We present TokenVerse -- a method for multi-concept personalization, leveraging a pre-trained text-to-image diffusion model.
Generative AI, Personalization, Machine Learning, Image Generation
108 points by 037 90 days ago | 22 comments
Show HN: I Made a SOTA Affordable Midjourney Alternative, Subscription Trap Free (ayecreate.ai)
AyeCreate makes it easy to Create, Generate and Craft Piece of Content, Designs or Media using State of the Art AI
AI, Generative AI, Open Source, Midjourney, Image Generation
12 points by srx9 94 days ago | 0 comments
Mann-E, breakthrough image generation platform with crypto payments (mann-e.com)
Our AI-powered platform helps you create stunning, unique images in seconds. Whether you're an artist, designer, or just looking to explore your creativity, we've got you covered.
Image Generation, Artificial Intelligence, Cryptocurrency
3 points by haghiri 105 days ago | 1 comments
NeuralSVG: An Implicit Representation for Text-to-Vector Generation (sagipolaczek.github.io)
NeuralSVG generates vector graphics from text prompts with ordered and editable shapes.
Generative AI, Artificial Intelligence, Image Generation, Text-to-Image
782 points by lnyan 107 days ago | 72 comments
How to generate OpenGraph images with Astro and Satori (skyfall.dev)
Generating OpenGraph images for your Astro site is an easy way to increase click-through rates and make link previews more appealing. Here's how to set them up!
Astro, OpenGraph, Web Development, SEO, Image Generation
8 points by JustSkyfall 110 days ago | 0 comments
1.58-Bit Flux (chenglin-yang.github.io)
We present 1.58-bit FLUX, the first successful approach to quantizing the state-of-the-art text-to-image generation model, FLUX.1-dev, using 1.58-bit weights (i.e., values in {-1, 0, +1}) while maintaining comparable performance for generating 1024 x 1024 images.
Machine Learning, Text-to-Image Generation, Image Generation, Deep Learning, Computer Science
11 points by quaintdev 114 days ago | 3 comments
NYT Quiz: Which Parts of These Images Are A.I.-Generated? (nytimes.com)
Artificial intelligence tools can fabricate entirely new images and videos. But they can now also make much smaller tweaks by inserting A.I. elements into genuine photographs, further blurring the line between what’s real and what’s fake.
Artificial Intelligence, Image Generation, Media, Technology, News
6 points by smcin 120 days ago | 1 comments
ByteDance INFP: The AI That Brings Images to Life (pdftranslate.ai)
Bytedance has introduced INFP, a powerful AI that can turn any single image into a lively character that can talk, sing, and interact with its surroundings.
Artificial Intelligence, Image Generation, Bytedance
13 points by sh_tomer 125 days ago | 2 comments
AI model for near-instant image creation on consumer-grade hardware (surrey.ac.uk)
A groundbreaking AI model that creates images as the user types, using only modest and affordable hardware, has been announced by the Surrey Institute for People-Centred Artificial Intelligence (PAI) at the University of Surrey.
Generative AI, Artificial Intelligence, Image Generation, Hardware
187 points by giuliomagnifico 136 days ago | 53 comments
Elon Musk's X launches image generator Aurora (techcrunch.com)
X, the Elon Musk-owned social network previously known as Twitter, has added a new image generator to its Grok assistant. However, after going live for a few hours on Saturday, the product seemed to disappear for some users.
Social Media, Artificial Intelligence, Image Generation
5 points by nancy_le 138 days ago | 0 comments
Trump received $273.2M in donations from tech executives and VCs (techmeme.com)
X adds Aurora, an AI image generator that appears to excel at photorealistic images and has few restrictions; it isn't clear if xAI trained Aurora itself
Politics, Artificial Intelligence, Image Generation
8 points by saomcomrad56 139 days ago | 6 comments
X gains a new image generator, Aurora (techcrunch.com)
X, the Elon Musk-owned social network previously known as Twitter, has added a new image generator to its Grok assistant. However, after going live for a few hours on Saturday, the product seemed to disappear for some users.
Social Media, Artificial Intelligence, Image Generation
9 points by elsewhen 139 days ago | 0 comments
Veo and Imagen 3: Announcing new video and image generation models on Vertex AI (cloud.google.com)
Generative AI is leading to real business growth and transformation. Among enterprise companies with gen AI in production, 86% report an increase in revenue1, with an estimated 6% growth. That’s why Google is investing in its AI technology with new models like Veo, our most advanced video generation model, and Imagen 3, our highest quality image generation model.
Generative AI, Google Cloud, Video Generation, Image Generation
30 points by srameshc 143 days ago | 15 comments
Researchers use AI to turn sound recordings into street images (news.utexas.edu)
AUSTIN, Texas — Using generative artificial intelligence, a team of researchers at The University of Texas at Austin has converted sounds from audio recordings into street-view images.
Artificial Intelligence, Computer Vision, Image Generation, Research
184 points by giuliomagnifico 145 days ago | 49 comments
FLUX.1 Tools (blackforestlabs.ai)
Today, we are excited to release FLUX.1 Tools, a suite of models designed to add control and steerability to our base text-to-image model FLUX.1, enabling the modification and re-creation of real and generated images.
Generative AI, Image Generation, Artificial Intelligence, Computer Vision
27 points by handfuloflight 155 days ago | 3 comments