15 stories tagged multimodal-models, newest first.
270 points by westsmith | 88 comments
A personal guide to AI image generation covering history, how diffusion and multimodal models work, costs, prompting, and integrating image APIs into code and agents.
12 points by ahmedahres | 2 comments
Reactor's product page for MiniMax FastH3 Omni, a faster-than-realtime video generation model with text, audio and image input, offered with a playground and API at $0.75/minute.
13 points by gmays | 3 comments
arXiv paper introducing UniEvo-VL, an on-policy self-distillation framework where a multimodal model uses its own self-critiques to improve image generation.
319 points by jjcm | 118 comments
Qwen blog post announcing Qwen 3.8 Omni Flash, a multimodal model, with a demo of parallel subagents reading video clips and doing web research.
1085 points by Philpax | 541 comments
Z.ai blog post announcing GLM-5.3-Flash, a natively multimodal 320B-parameter (18B active) model with hybrid sparse/linear attention, claiming strong coding and agentic results.
930 points by thisisauserid | 470 comments
Google's Gemini API documentation page for Gemini 3.7 Flash, the next multimodal reasoning model in the Gemini 3 series.
546 points by ThouYS | 128 comments
Black Forest Labs blog post announcing FLUX 3, multimodal flow models spanning image, video, audio and action as real-world models for visual intelligence.
1007 points by rvz | 379 comments
Google blog post announcing Gemma 4 12B, an encoder-free multimodal model designed to run on laptops with mobile-first efficiency and advanced reasoning.
451 points by asenna | 127 comments
Blog post describing how the author used Gemma 4 running locally on a five-year-old MacBook to index a year of personal video footage overnight.
393 points by danielhanchen | 182 comments
Qwen team blog post announcing Qwen3.5, a model family aimed at native multimodal agent capabilities.
331 points by LorenDB | 73 comments
Ollama blog post from May 15, 2025 announcing a new engine for running multimodal models locally.
976 points by meetpateltech | 524 comments
OpenAI's March 2025 announcement introducing native image generation in GPT-4o, available in ChatGPT.
![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)
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.
426 points by minimaxir | 67 comments
Medium post by Aksh Garg describing Llama 3-V, an open-source multimodal model claimed to match GPT-4V while being 100x smaller and trained for under $500.
360 points by swyx | 92 comments
Yi Tay's blog post on the experience of training large language models from scratch at a startup (Reka), covering compute, infrastructure, and lessons learned.