alfredplpl
/

qwen-image-ja-text-test

Model card Files Files and versions

日本語のテキストを生成できそうなQwen-Image用LoRA

weight for ComfyUI (WIP)

weight for diffusers (WIP)

作り方

alfredplpl/image-text-pairs-ja-cc0をmusubi tunerでLoRA学習しただけ。現在、20 A100時間かかっている。

ギャラリー

50stepsぐらい推論してください

prompt: Japanese black and white manga style, a close-up of a smiling girl saying "俺がガンダムだ" with the speech bubble.
negative prompt: 3d, cg, photo

prompt: Japanese anime style, a girl is holding the sign saying "人間性を捧げよ".
negative prompt: 3d, cg, photo

prompt: This image is saying "ありがとう". The background is white. The letter is black.
negative prompt:

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

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

Model tree for alfredplpl/qwen-image-ja-text-test

Base model

Qwen/Qwen-Image

Adapter

(49)

this model

Dataset used to train alfredplpl/qwen-image-ja-text-test

Spaces using alfredplpl/qwen-image-ja-text-test 2