Downloads · 30 days
15
6% of all-time downloads
flux-krea-nolan-lora
ksampath/flux-krea-nolan-lora
flux-krea-nolan-lora is a text-to-image model from ksampath. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as apache-2.0.
All-time downloads
237
Public
Repo size
13.5 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.safetensors13.4 MB · 99%
At a glance
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Access
- Public
- Created
- Aug 7, 2025
- Updated
- Aug 9, 2025
- SHA
- 61e491f7
Try a prompt
Base models
Model card
From the Hugging Face model README
Flux1.Krea-dev-nolan
<Gallery />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
- A flying object going towards a supernova
Nolan LoRA
Base Image
- Two spy agents running up a stairwell, tense
Nolan LoRA
Base Image
Trigger words
You should use <nolan-style> to trigger the image generation.
Download model
Download them in the Files & versions tab.
- Task
- Text-to-Image
- Library
- diffusers
- License
- apache-2.0
- Fal Ai
- live
- Wavespeed
- live
- Created
- Aug 7, 2025
- Updated
- Aug 9, 2025