<h1 id="fixed-the-issue-now-it-works-with-gguf-models-too">Fixed the issue, now it works with gguf models too</h1><h3 id="image-repair-flux.2-klein9b">Image Repair Flux.2-Klein9B</h3>Hey everyone! This is my second LoRa. So, I took the original idea from <a target="_blank" rel="ugc" href="https://civarchive.com/models/2364648/image-repair?modelVersionId=2659402">Link</a><h3 id="how-it-works:">How it works:</h3>I trained this using a LoRA subtraction method (clean originals vs. degraded/pixelated versions). Because it extracts the exact "delta" of the degradation, it only targets the artifacts and noise without altering the core of image. It may not work with all images, on very complex detailed patterns it can hallucinate like the original flux2, try a different seed. Also, as you can see from the examples, the original flux2 saturation is poorly controlled.<h3 id="training-details:">Training details:</h3>Latent: 512X512 (Also lora work with higher resolution and other aspect ratio)I tried 1024 latent size when training, but OOM forced me to optimize the settings.Lora rank: 16Steps: 2000Grad_accum: 4Source images: 227 (all created in 2k/4k NanoBananaPro + Some Flux2.Kein9B)These settings were before lora was weakened. She was initially retrained. this is 0.3 Strength of original train.As with the author of the idea, all settings were created by a neural network (not chatgpt) and Python scripts were used for configuration.<h3 id="recommended-settings:">Recommended Settings:</h3><ul><li>LoRA Weight: <code>1.0</code></li><li>Trigger Words: make image high quality</li><li>CFG: 1</li><li>Steps: 4-6</li></ul>I hope for positive feedback, but I hope you find this version useful.Also think it can be improved further. Later, soon...Do not use lora with the ImageScaleToTotalPixels node. Some image with this node is totally sh*t

Files with SHA256: 2fe4a6bf44f6caf28e994b5675e1bc70fe806c09ae8d49cc083cac2adeee1ce2