VuongKB/Fluxgym AI Training.md

created, id, links, modified, summary, tags, title

created	id	links	modified	summary	tags	title
2026-04-05T05:40:04+00:00	85578143-5ecf-465f-a8a9-3d25e57e2c7f		2026-04-05T05:40:04+00:00	This note outlines the configuration parameters for training a Flux model image generation pipeline, specifying essential requirements like repeating input images 5 times, resizing to 1024 for high quality, and targeting 20-30 images, along with detailed advanced settings such as learning rate, LoRA rank, noise parameters, and batch size.		Fluxgym AI Training

Suggested Repeat Train Images 5 Resize to 1024 for HQ images Flux wants 20-30 images Advanced: learning rate : 5e-4 save every n epochs: 1 lora rank: 16 enable bucket: true flip-aug: for styles minimum snr gamma: 5 multires noise discount: 0.3 multires noise iteration: 6 noise offset: 0.1 train batch size: 2-4