ksampath/flux-krea-fincher-lora

Flux1.Krea-dev-fincher

<Gallery />

Model description

Overview

Finetuned LORA off FLUX.1-Krea-dev that better captures the style of David Fincher. The training took ~11 H200 hours to train, and is optimized in a number of ways, including but not limited to: VAE caching, image interpolation, optimized attention via xformers, torch.compile(), Cosine LR annealing. The dataset of ~200 images was curated to especially capture the width of the directorial body of work, with captioning also focusing on style of the model.

Uses

• —Flux 1 - Krea dev (black-forest-labs&#x2F;FLUX.1-Krea-dev) as the base model for training
• —uv for package management
• —ruff for code quality
• —ty for type checking
• —modal for infrastructure
• —shotdeck (https:&#x2F;&#x2F;shotdeck.com&#x2F;) for training stills and data
• —Qwen 2.5VL - 3B for image captioning

Comparison

1. 1.Urban decay around detectives walking

Base Model

Fincher LoRA

1. 1.College kids bunking together in a house

Base Model

Fincher LoRA

Trigger words

You should use <fincher-style> to trigger the image generation.

Download model

Download them in the Files & versions tab.