This LoRA was trained on ~100 vintage photos shot on Kodachrome film and attempts to capture some of it's characteristic color capabilities with a rich saturation, especially in reds and a very fine grain. It also imbues a vintage look to people and buildings and can be pushed or pulled from this look with prompting.

Kodachrome FLUX

Trained on ~100 image caption pairs with a batch size of 4 using the prodigy optimizer for 2000 steps with a slightly modified version of the ai-toolkit repo.

FLUX-Kodachrome-KDCRM.safetensors

Kodachrome FLUX v1.0

From <a href="https://civitai.com/models/699477/kodachrome-flux" rel="ugc noopener noreferrer nofollow" target="_blank">https://civitai.com/models/699477/kodachrome-flux</a> and <a href="https://civitai.com/models/464306/kodachrome-sdxl" rel="ugc noopener noreferrer nofollow" target="_blank">https://civitai.com/models/464306/kodachrome-sdxl</a>

Files with SHA256: f4ff2a5bde577eebb735d34122e1e5799587f81e7d9721d395ad11595df00611