another badly trained lorav3 latest versionv1 has more fanart of him in datasetv0.8 is same as above but at 8th epochv2 has more game screenshots in dataset and lower learning rate and a failed experimentall bad xdtrained on NAIprompts like teamred/teamblu, red jacket/blue jacket can help change the team color of soldierhelmet, red/blue jacket, bandolier, two grenades, covered eyes, on prompts can help

TF2 Soldier Lora

cleaned up dataset a bit, changed settings

Files with SHA256: d217a98f3487b4555e1d7171e7b1b9675daeed5351e70718ba938f781ca982db