Flux1.Krea-dev-nolan

Prompt
Two spy agents running up a stairwell, tense
Prompt
A flying object going towards a supernova

Model description

Model description

Overview

Finetuned LORA off FLUX.1-Krea-dev that better captures the style of Christopher Nolan. 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/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://shotdeck.com/) for training stills and data
  • Qwen 2.5VL - 3B for image captioning

Comparison Images

  1. A flying object going towards a supernova

Nolan LoRA Nolan LoRA Base Image Base Image

  1. Two spy agents running up a stairwell, tense Nolan LoRA Nolan LoRA Base Image Base Image

Trigger words

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

Download model

Download them in the Files & versions tab.

Downloads last month
31
Inference Examples
Examples
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for ksampath/flux-krea-nolan-lora

Adapter
(19)
this model