Please post the first picture directly here in the Model Gallery. This is the best way to support creators ♡
This version doesn't require any trigger words - Best Strength: 0.8
To create this LoRA, I initially downloaded approximately 200 photos from Flickr, sourced from top photographers. I then edited roughly one-third of the images in Photoshop, applying my desired effect. Another third I modified using the Image to Image method with Flux. The remaining third I left unchanged.
Due to the large image count and limited VRAM on my graphics card, I processed each group separately. Finally, I merged these three resulting models with a previous model I had created from images by a landscape photographer.
Unfortunately, the initial LoRA was unsatisfactory. Following a friend's suggestion, I reduced the image count to 90 carefully selected photos and incorporated a few images from Civitai. Using the same three-group process, I edited and processed the images. I then merged four LoRAs with varying weights, creating over 20 LoRA variations and conducting more than 500 tests. Finally, I achieved the desired result, which is the uploaded LoRA.
This LoRA subtly enhances contrast, adds a touch of realism and fantasy, and increases detail. It also imparts a slightly aged look, introduces subtle dirt and dust, and often generates fog in landscapes. In portraits, it tends to add a sunlight effect. It can also give images, particularly vehicles, a classic and aged appearance, and generally darkens the overall mood.
However, being a beginner, I'm aware that this LoRA may still contain issues and bugs. I would greatly appreciate it if you could help identify these problems so I can fix and improve the model.
Hope you get a lot of beautiful results ♥