The main goal was to make more 'live' images with livelier emotions and more dynamic poses and slightly amateurish quality (also can produce high quality images). At this moment there are still some issues with hands, but less then in first version
Setting i use in ComfyUI:
CFG=1, Guidance =2.5, Scheduler=Beta, Sampler=dpmpp_2m, Steps=40
V3 (WIP)
Working on improvement of hands, feet, poses
V2
Changed half of images in dataset, changed prompting style, improved hands, less 'flashlight effects' at night scenes and overall LoRa quality improvement (i hope).
In this version it's unnecessarily to use tons of 'trigger words' like in V1. Just add some of them that i mentioned in trigger words
V1
Trained another ******* lora (that's already been done a lot around here).
Still, I took some pictures from my dataset on 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 only confused the model. In the dataset there are many different gradations of quality, like:
1) High-resolution photo, shot on a mobile phone, no visible artifacts, clear and sharp
2) Low-resolution, ******* photo shot on 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 their combinations and variations. I think i'll remove such in next version. But this one working the best for me:
Low-resolution, ******* photo shot on digital camera, no visible jpeg artifacts, slightly noisy
Also i'm planing to train a checkpoint and if you can help me with resources for example, I will be ready to cooperate (you can DM me). And in general open to suggestions for work with AI =)
