rh-2085421033338785793-lora

中文 RunningHub API RunningHub International RunningHub China

Description

Field Content
Model Name rh-2085421033338785793-lora
Model Type LoRA (text-to-image)
Platforms ComfyUI / RunningHub / Hugging Face
Author RunningHub-@蛋炒饭
Original https://www.runninghub.cn/model/public/2085421033338785793
Try online https://www.runninghub.ai
https://www.runninghub.cn/runninghub-api-doc-en/

About this model

折磨人的吐血之作,本lora为人像精修写真特化,不是写实,不是真实,不是写实,不是真实,不是写实,不是真实。

食用方式:zimage(不带trubo)直出。

采样步数8,搭配8步加速lora食用,建议加速权重0.45。可参照我的工作流(最简单的)。

推荐权重0.4-0.5。

推荐CFG1-2(越高越遵循提示词,但是也不能太高,太高会过拟合)。

支持直出300万像素。

已知问题:小概率出现肢体、手指、脚趾错误,角色不好看,画面不好看。

解决方式:让cfg大于1、抽几次卡,降低权重。

This repository provides rh-2085421033338785793-lora weight files. You can load them on RunningHub.

Finetuned from: Z-image-base

Files

File Size Purpose
dfrxstyle20260801_sig_HN_000020709.safetensors 324 MiB LoRA weights

License

Published by RunningHub on behalf of the author. Copyright remains with the author. Follow the original project or upstream license.

Training at RunningHub

Train models on RunningHub: https://www.runninghub.ai/page-model

Run Seedance 2.5 with RunningHub API: https://www.runninghub.ai/call-api/api-detail/2133100000000700025

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