README.md

metadata

tags:
  - text-to-image
  - lora
  - diffusers
  - template:diffusion-lora
widget:
  - output:
      url: images/Cinematic Style Generator Image (3).webp
    text: >-
      A group of foxes and badgers in an underground tunnel looking down at a
      patient, in Wes Anderson's style
  - output:
      url: images/Cinematic Style Generator Image.webp
    text: A pastel colored dollhouse
base_model: black-forest-labs/FLUX.1-Krea-dev
instance_prompt: <anderson-style>
license: apache-2.0

Flux1.Krea-dev-anderson

Prompt

A group of foxes and badgers in an underground tunnel looking down at a patient, in Wes Anderson's style

Prompt

A pastel colored dollhouse

Model description

Overview

Finetuned LORA off FLUX.1-Krea-dev that better captures the style of Wes Anderson. 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/welcome/home) for training stills and data
• Qwen 2.5VL - 3B for image captioning

Comparison Images

1. A pastel colored dollhouse Base Model Anderson LoRA

2. A group of foxes and badgers in an underground tunnel looking down at a patient, in Wes Anderson's style

Base Model Anderson LoRA

Trigger words

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

Download model

Download them in the Files & versions tab.