Downloads · 30 days
1.1K
0% of all-time downloads
alvdansen/flux-koda
flux-koda is a text-to-image model from alvdansen. Use it when you need an image from a text prompt. It is set up for diffusers. The card lists the license as creativeml-openrail-m.
Downloads · 30 days
1.1K
0% of all-time downloads
All-time downloads
281K
Public
Repo size
698 MB
Likes
252
Public
Click a slice to open those files.
.safetensors687 MB · 99%
From the Hugging Face model README
Koda captures the nostalgic essence of early 1990s photography, evoking memories of disposable cameras and carefree travels. It specializes in creating images with a distinct vintage quality, characterized by slightly washed-out colors, soft focus, and the occasional light leak or film grain. The model excels at producing slice-of-life scenes that feel spontaneous and candid, as if plucked from a family photo album or a backpacker's travel diary.
Words that can highlight interesting nuances within the model:
kodachrome, blurry, realistic, still life, depth of field, scenery, no humans, monochrome, greyscale, traditional media, horizon, looking at viewer, light particles, shadow

You should use flmft style to trigger the image generation.
Weights for this model are available in Safetensors format.
Download them in the Files & versions tab.