<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Text-Generation on Noureddine RAMDI</title><link>https://ramdi.fr/tags/text-generation/</link><description>Recent content in Text-Generation on Noureddine RAMDI</description><generator>Hugo</generator><language>en</language><lastBuildDate>Sat, 23 May 2026 20:41:27 +0000</lastBuildDate><atom:link href="https://ramdi.fr/tags/text-generation/index.xml" rel="self" type="application/rss+xml"/><item><title>OmniGen2: a unified multimodal generation model with separate decoding paths for text and images</title><link>https://ramdi.fr/github-stars/omnigen2-a-unified-multimodal-generation-model-with-separate-decoding-paths-for-text-and-images/</link><pubDate>Sat, 23 May 2026 20:41:14 +0000</pubDate><guid>https://ramdi.fr/github-stars/omnigen2-a-unified-multimodal-generation-model-with-separate-decoding-paths-for-text-and-images/</guid><description>OmniGen2 unifies visual understanding, text-to-image generation, and image editing using distinct decoding pathways for text and images, built on Qwen-VL-2.5 with CPU offloading for accessibility.</description></item></channel></rss>