hinablue/[Qwen Image] Asian Mix Lora
v3.0 - Q21 - rank64 使用自行製作的訓練器訓練（ https://github.com/hinablue/qwen-image-21-trainer ），資料集為 6,000 筆，使用 Rank 64 做訓練，與 v2.0 做 SVD 融合而成的 Lora。權重在 0.8 以下較為穩定，肢體可能還是會有異常狀況，請自行斟酌使用。 Trained using a custom-built trainer ( https://github.com/hinablue/qwen-image-21-trainer ) with a dataset of 6,000 images, using Rank 64, and merged with v2.0 via SVD to create this LoRA. It is more stable at a weight below 0.8. Limb/anatomy issues may still occasionally occur, so please use at your own discretion. 自作のトレーナー ( https://github.com/hinablue/qwen-image-21-trainer ) を使用し、6,000枚のデータセット、Rank 64にて学習を行いました。その後、v2.0
| Author / organization | hinablue |
|---|---|
| Downloads | 7.3K (as reported by Civitai) |
| Likes | 326 |
| Task | text-to-image |
| Created | 1 October 2026 |
| Last updated at source | — |
Popularity, last 3 days
7,299 now (+150 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from hinablue
Silytics shows public metadata from Civitai and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.