MoYou/flux1East-GGUF_Q4_0
更适合东方宝宝的flux 使用20000余张精选数据以1024×1152分辨率训练1600+小时 ,加入了东方文化内容,具有丰富的多样性,避免了面部趋近 本次同时制作了三种格式精度: fp16: flux1East-fp16 - dev | Flux Checkpoint | Civitai fp8: flux1East-fp8 - dev | Flux Checkpoint | Civitai GGUF-Q4_0: 本模型卡 每个格式精度下五个模型类别: dev (fp16,fp8,gguf均有极高的质量)、 schnell (4步快速模型)、 fill 、 canny 、 depth 全系兼容redux(搭配redux使用时flux引导:20) 可继续训练,可作底模训练lora 可以完美兼容majicFlus生态的lora 一定程度兼容原生flux lora(写实降权,非写实加权) 令人惊喜的 schnell(4步快速模型)也有着较高的出图质量 以下是各精度对比: 使用建议: webui-forge中: 基础设置: 采样方法 (Sampler):euler 调度类型 (Schedule type):simple 迭代步数 (Steps):20(速度快)、30(性价比高)、50(更稳定的效果) Hires Distilled CFG Scale:3.5 Hires CFG Sca
| Author / organization | MoYou |
|---|---|
| Downloads | 2.8K (as reported by Civitai) |
| Likes | 154 |
| Task | text-to-image |
| Created | 12 March 2025 |
| Last updated at source | — |
Popularity, last 3 days
2,758 now (+5 since 2026-10-15). Counts as reported by the source, snapshotted daily by Silytics.
More from MoYou
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 Information may be incomplete or out of date.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.