Update README.md

README.md

@@ -1,5 +1,29 @@
----
-license: other
-license_name: other
-license_link: LICENSE
----
+license: other
+license_name: other
+license_link: LICENSE
+---
+The main goal was to achieve the quality of the photo as if it was taken on a phone, in motion, and to make realistic night photos. Additionally, the emotions were improved to make them more alive, not as if people are posing in a studio.
+
+V2 (WIP)
+
+Already collecting more images for the dataset. The newer version must be better.
+
+V1
+
+Trained another amateur LoRA (that's already been done a lot around here).
+
+Still, I took some pictures from my dataset from the 2000s and added another 700 pictures. It came out pretty good so far, but there is a controversial point about quality optimization. I was hoping it would help control the quality, but as I see it, it only confused the model. In the dataset, there are many different gradations of quality, such as:
+
+1) High-resolution photo, shot on a mobile phone, no visible artifacts, clear and sharp.
+
+2) Low-resolution, amateur photo shot on a digital camera, no visible JPEG artifacts, slightly noisy.
+
+3) Medium-resolution photo, shot on a mobile phone, slight graininess due to low-light conditions, no significant digital artifacts.
+
+And other combinations and variations. I think I'll remove such in the next version. But this one is working the best for me:
+
+Low-resolution, amateur photo shot on a digital camera, no visible JPEG artifacts, slightly noisy.
+
+Also, I'm planning to train a checkpoint, and if you can help me with resources, for example, I will be ready to cooperate (you can DM me). In general, I am open to suggestions for work with AI =)
+
+P.S.: I am not the original author of this model. The author and link to the original model: ["https://civitai.com/models/796382?modelVersionId=890545"](https://civitai.com/models/796382?modelVersionId=890545)