I present my first lora model trained with local fluxgym, I used 20 high quality imagesNote: Carla is a fictional model, the images used in the training were generated by the Latina Girls model, this Lora does not represent a real person.It is strictly prohibited to distribute, inside and outside civit ai, this model or respond anywhere or hosting services, in third-party image generation services, you can use it for personal use, if you know who someone distributed it without my consent , report it immediatelyTo use the lora model you need to insert the token: clmdbl86 e class: womanRecommended strength:clmdbl86&lt;lora:carla-model:0.90&gt;clmdbl86&lt;lora:carla-model:0.85&gt;clmdbl86&lt;lora:carla-model:0.75&gt;clmdbl86&lt;lora:carla-model:0.65&gt;I recommend using the <a target="_blank" rel="ugc" href="https://github.com/Bing-su/adetailer">Adetailer</a> extension.Recommended settings:Standard resolutions 512 x 640, 640x 768x960, 896 x1152Resolution: 540x540 mark the Hires.fix, result 1080 x 1080 pixelResolution: 540x960 mark the Hires.fix, result 1080 x 1920 pixelUse these recommended settings for generation:Sampling method: Euler/simpleSampling steps: 18-20Distilled CFG Scale: 3,5 - 8Skip clip: 0Sampling method: Euler/betaSampling steps: 18-20CFG Scale: 3,5 -8Skip clip: 0

carla model

This is a beta version and may contain bugs and errors. Before jumping the gun, please provide feedback with comments like: "It doesn't work properly, it's no good!" I'll ignore it, as I'm still learning how to train LoRas in Flux Dev1, and I have no intention of publishing LoRa models with bugs. However, I ask for patience; there are some very demanding people around here.

Files with SHA256: dbb86cb902f0d2d03bff172fe8c76a845a5c2ad84fadbd4fd99887f122e4636b