Training Text-to-Image Models Without a VAE(linum.ai)
49 points by schopra909 | 14 comments
Linum research blog post introducing Pyramid-JiT, a multiresolution prediction method to speed convergence of VAE-free pixel-space text-to-image models.
#text-to-image on Hacker News
13 stories tagged text-to-image, newest first.
FLUX 3 Image(bfl.ai)
426 points by minimaxir | 95 comments
Black Forest Labs product page for FLUX 3 Image, an image generation model marketed with fine-grained pixel control, with links to try it and read docs.
Qwen Image 2.1(qwen.ai)
711 points by jmillikin | 189 comments
Qwen team blog post announcing Qwen-Image-2.1, a compact, efficient, unified image generation and editing model.
Qwen-Image-3.0: Rich Content, Authentic Details, Deep Knowledge(qwen.ai)
539 points by ilreb | 211 comments
Qwen team blog post announcing Qwen-Image-3.0, an image generation model emphasizing rich content, authentic details, and deep knowledge.
Qwen-Image-2.0: Professional infographics, exquisite photorealism(qwen.ai)
378 points by meetpateltech | 160 comments
Qwen team blog post announcing Qwen-Image-2.0, an image generation model focused on professional infographics and photorealistic output.
![Screenshot of github.com: DeepSeek releases Janus Pro, a text-to-image generator [pdf]](https://hn.urlbox.com/shots/renders/2025/1/27/0036db74-451f-4baf-bf60-d30784522dd5.jpg)
DeepSeek releases Janus Pro, a text-to-image generator [pdf](github.com)
852 points by reissbaker | 623 comments
GitHub file page in DeepSeek's Janus repository hosting the Janus-Pro technical report PDF, a multimodal understanding and text-to-image generation model.
Flux: Open-source text-to-image model with 12B parameters(blog.fal.ai)
627 points by CuriouslyC | 185 comments
Fal.ai blog post announcing availability of Flux, a 12B-parameter open-source text-to-image model, on the fal platform.
Stable Diffusion 3: Research Paper(stability.ai)
446 points by ed | 88 comments
Stability AI blog post announcing the research paper behind Stable Diffusion 3 and its Multimodal Diffusion Transformer (MMDiT) architecture.
Show HN: Real-time image generation with SDXL Lightning(fastsdxl.ai)
374 points by treesciencebot | 85 comments
A web demo for real-time text-to-image generation using SDXL Lightning, with prompt and seed inputs and a link to fork the code on GitHub.
Stable Diffusion 3(stability.ai)
900 points by reqo | 635 comments
Stability AI's announcement post for Stable Diffusion 3, its next-generation text-to-image generative model.
Stable Cascade(github.com)
666 points by davidbarker | 154 comments
GitHub repository for Stability AI's Stable Cascade, a text-to-image diffusion model, with code for training and inference.
DALL·E 3(openai.com)
476 points by davidbarker | 357 comments
OpenAI's product page announcing DALL·E 3, a text-to-image model that follows prompts with more nuance and detail than earlier versions.
Stable Diffusion WebGPU demo(islamov.ai)
427 points by aislamov | 98 comments
An in-browser demo that runs Stable Diffusion image generation locally using WebGPU, with prompt inputs and a model loader.