🖼 Trained the Blur Background Kontext LoRA with AI Toolkit on an RTX 3090 using ML-Depth-Pro outputs.Results looked good after 250 steps (~25 mins).When combined with Kontext Lighting, it outperforms ML-Depth-Pro in just 6–8 steps.Thanks to @ostrisai ❤ @bfl_ml ❤ ML Depth Pro Team ❤Thanks to Steve ❤ for the GPU resources. (v2) 🧬code: <a target="_blank" rel="ugc" href="https://github.com/ostris/ai-toolkit">https://github.com/ostris/ai-toolkit</a>🧬code: <a target="_blank" rel="ugc" href="https://github.com/apple/ml-depth-pro">https://github.com/apple/ml-depth-pro</a>📦blur background: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1809726">https://civarchive.com/models/1809726</a>📦unblur background: <a target="_blank" rel="ugc" href="https://civarchive.com/models/1812015">https://civarchive.com/models/1812015</a><span style="background-color:rgb(26, 27, 30);color:rgb(193, 194, 197);font-family:-apple-system, BlinkMacSystemFont, &quot;Segoe UI&quot;, Roboto, Helvetica, Arial, sans-serif, &quot;Apple Color Emoji&quot;, &quot;Segoe UI Emoji&quot;;font-size:16px">📋Note: Blur, trained with Gaussian blur, works with Gaussian blur. If you have pairs of blurred and sharp images from a camera lens (same image different aperture), I'd love to use them for training.Enjoy! ❤

Files with SHA256: ee0e22a6be5ae188349c0b760bb35392007095b7869a4836362f8702383b71a2