<p>This is a WF for a Flux and SDXL Lora trainer which uses minimal VRAM and puts out excellent results. It's based on:</p><div data-youtube-video><iframe allowfullscreen="true" autoplay="false" disablekbcontrols="false" enableiframeapi="false" endtime="0" ivloadpolicy="0" loop="false" modestbranding="false" origin playlist src="https://www.youtube.com/embed/m3ENCAwWDXc" start="0" width="640" height="480"></iframe></div><p>This guy's work. I've refined it crushed it down to what's needed and made it much tidier. Added a universal Renaming/Keyword node and an INT node to govern the steps taken per iteration to make life easier and added 40 potential dataset nodes should you need em.</p><p>Resize large images to 1024 as their largest dimension.</p><p>0.0003 learning rate at 100 steps as a 'Tester' (don't be surprised if you get a black and white preview shot first time) then 450 in a 'Big Step' to get over the hump of training with 75 steps a piece after that so you can test them out.</p><p>5 Nodes are specifically able to drop their min bucket res so you can refer to folders with smaller resolution pics in those nodes.</p><p>No captioning necessary works very well without them.</p><p>I advise restarting after each training session to ensure whatever cache is clear of old info.</p>

Flux/SDXL Lora Trainer (8GB Vram)

<p>Works with XL or Flux just swap out the model. Nomenclature may use SDXL and Flux interchangeably.</p>

Files with SHA256: de37bca204d78584476436eb99bfee17b15d444cdf4d33a165d25c62b0ca1b52