









a LoRA trained on approximately 50 images with a nostalgic vintage appeal, this LoRA works best with my Flux Latent Upscaler workflow or paired with Koda Flux at about 0.30.
The outputs shared are all using the Flux Latent Upscaler workflow and the LoRA strength set to 0.7 I tested a range of subjects and it does surprisingly well with a lot of scenes and environments. When paired with Koda Flux it helps to add more realism to skin details while maintaining the early 80s styling of the overall image.
As you can see in the gallery I've tested it with a couple of different scenes and it holds up well despite being trained primarily on portrait and street photography styles.
The training images were captioned using a Joy Caption Batch script for Python, the captions are rich with the trigger at the beginning of each caption file. Training took just under 2 hours.
If you enjoy this resource please send BUZZ ⚡️so I can keep experimenting and sharing. Please share your images in the gallery after downloading them, by sharing them in the gallery the system gives creators 200 buzz to help with generating and training.
Trigger keyword: '3ighti3s'
Recommended strengths: 0.7 - 0.9
1. 재게시된 모델의 권리는 원 제작자에게 있습니다.
2. 모델 원작자가 모델을 인증받으려면 공식 채널을 통해 SeaArt.AI 직원에게 문의하세요. 저희는 모든 창작자의 권리를 보호하기 위해 노력합니다. 인증하러 이동
