<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom"><channel><title>Ai-Image-Generation on My blog</title><link>https://sanj.dev/tags/ai-image-generation</link><description>Recent content in Ai-Image-Generation on My blog</description><generator>Hugo -- gohugo.io</generator><language>en</language><lastBuildDate>Wed, 20 May 2026 00:00:00 +0000</lastBuildDate><atom:link href="https://sanj.dev/tags/ai-image-generation/index.xml" rel="self" type="application/rss+xml"/><item><title>LoRA Training Guide 2026: Kohya SS, FLUX.1/FLUX.2 &amp; VRAM Optimization (8GB-80GB)</title><link>https://sanj.dev/post/lora-training-2025-ultimate-guide</link><pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate><guid>https://sanj.dev/post/lora-training-2025-ultimate-guide</guid><description>Complete step-by-step LoRA training guide for 2026. Compare Kohya SS vs AI-Toolkit, train FLUX.1 and FLUX.2 LoRAs, and optimize VRAM from 8GB to 80GB with fused backward pass settings.</description></item><item><title>Train Your Own Stable Diffusion LoRA in 2026: Complete Guide</title><link>https://sanj.dev/post/train-stable-diffusion-lora-self-portraits</link><pubDate>Wed, 20 May 2026 00:00:00 +0000</pubDate><guid>https://sanj.dev/post/train-stable-diffusion-lora-self-portraits</guid><description>How to train a character LoRA for Stable Diffusion in 2026. Dataset prep, tool setup, training parameters, and inference. Covers Kohya SS, FluxGym, and ComfyUI workflows.</description></item></channel></rss>