rh-qwen-image-2.1-loras-lora
Description
| Field | Content |
|---|---|
| Model Name | rh-qwen-image-2.1-loras-lora |
| Model Type | LoRA (text-to-image) |
| Platforms | ComfyUI / RunningHub / Hugging Face |
| Author | RunningHub-@SVIP专属 |
| Original | https://www.runninghub.cn/model/public/2102767669668827138 |
| Try online | https://www.runninghub.ai |
| https://www.runninghub.cn/runninghub-api-doc-en/ |
About this model
Qwen2.1_Anime_一致性
- 概述：一款旨在增强动漫风格图像编辑过程中角色一致性的 LoRA。
- 训练数据：主要基于角色模型表（4视图参考）和各种面部表情编辑进行微调。
- 状态：⚠️实验性 >注意：此模型目前处于实验阶段。它主要用于测试和评估 Qwen Image 2.1 的最佳训练参数。因此，具体的编辑效果和输出稳定性无法得到严格保证。
⚙️ 推荐参数
为确保最佳性能，请遵循官方基础型号设置：
- 采样步骤：按照 Qwen-Image 2.1 的官方推荐设置进行操作。
- CFG 缩放：请按照 Qwen-Image 2.1 的官方推荐设置进行操作。
- LoRA 权重：建议从 `0.6` 到 `0.8` 之间开始测试，并根据您的具体编辑需求进行调整。
This repository provides rh-qwen-image-2.1-loras-lora weight files. You can load them on RunningHub.
Finetuned from: Qwen-image
Files
| File | Size | Purpose |
|---|---|---|
Qwen2.1_Anime_consistency.safetensors |
160 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
- RunningHub：https://www.runninghub.ai
- RunningHub 中国站：https://www.runninghub.cn
- RunningHub API 文档：https://www.runninghub.cn/runninghub-api-doc-cn/
- RunningHub API Documentation：https://www.runninghub.cn/runninghub-api-doc-en/
- Original project: https://www.runninghub.cn/model/public/2102767669668827138
- Author page: https://www.runninghub.cn/user-center/1929731488613310465