This model has been trained on editorial photographs taken for Vogue in the 1960s. It replicates the angled lighting, clean backgrounds, and buttery focus of the original photographs. Perhaps more importantly, it also captures the distinctive hair, jewellery, and clothing styles of Sixties high fashion. Bring the past into the present with this elegant LoRA.
Description
Trained on the same source images as v1.0, but with a rank of 128 instead of 32. Training to a higher rank increases the file size, but also improves this LoRA's interactions with Textual Inversion (TI) embeddings.
FAQ
Comments (3)
Amazing, very impressive work, will you try SDXL 1.0?
Thank you! Yes, I've started work on training SDXL LoRAs. It's been slow going because ControlNet isn't available for SDXL yet - once that is resolved I hope to have some models to share.
Awesome aesthetics and a fun lora! It does tend to give you the same (attractive) face for women sometimes.
Details
Available On (1 platform)
Same model published on other platforms. May have additional downloads or version variants.