quarterturn
/

qwen-image-20b-city

Model card Files Files and versions

You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

Log in or Sign Up to review the conditions and access this model content.

A Qwen-image 20b LoRA for emulating the City the Animation style and characters.

Note:

Every caption in the dataset began with "City-style " so if you use that, you should trigger the LoRA
I made no effort to identify characters in each image, but if you properly describe them, you should get them
the dataset was captioned by my molmo-image captioning tool (found here on Huggingface)

Trained using musubi-trainer with the defaults for qwen-image using 553 1328x747 images for 16 epochs

Downloads last month: -

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for quarterturn/qwen-image-20b-city

Base model

Qwen/Qwen-Image

Adapter

(481)

this model