vafipas663

Still work in progress, checkpoints are being uploaded on the go Current best: LoRA A: qwen-edit-enhance64-v3000001000, LoRA B: qwen-edit-enhance000004250 V4 Candidates LoRA A: qwen-edit-enhance-v4-16a000003000/1000, LoRA B: qwen-edit-enhance-v4-64a000003750/4750 LoRA A and LoRA B are meant to be wired one after another Prompt: Enhance image quality, followed by textual description of the scene. The more descriptive it is, the better the upscale effect will be All images below are from 8 step Lighting LoRA. ModelSamplingAuraFlow is a must, shift must be kept below 0.3. With higher resolutions, such as image 3, you can set it as low as 0.02 Samplers - LCM (best), EulerAncestral, then Euler Schedulers all work and give varying results in terms of smoothness Trained on a filtered subset of Unsplash-Lite and UltraHR-100K at 2.4MP Style: photography Subjects include: landscapes, architecture, interiors, portraits, plants, vehicles, abstract photos, man-made objects, food Trained to recover from: > Low resolution up to 16x > Oversharpened images > Noise up to 50% > Gaussian blur radius up to 3px > JPEG artifacts with quality as low as 5% > Motion blur up to 64px > Pixelation up to 16x > Color bands up to 3 bits > Images after upscale models - up to 16x Not trained on: 2d, illustrations, artworks, text, graphics, CGI