| --- |
| tags: |
| - comfyui |
| - lora |
| --- |
| |
| # rh-lora |
|
|
| [](README_cn.md) |
| [](https://www.runninghub.ai/call-api?utm_source=huggingface&utm_medium=badge&utm_campaign=api_promotion&utm_content=rh-2094270900408512514) |
| [](https://www.runninghub.ai?utm_source=huggingface&utm_medium=badge&utm_campaign=model_upload&utm_content=rh-2094270900408512514) |
| [](https://www.runninghub.cn?utm_source=huggingface&utm_medium=badge&utm_campaign=model_upload&utm_content=rh-2094270900408512514) |
|
|
| ## Description |
|
|
| | Field | Content | |
| |---|---| |
| | Model Name | rh-lora | |
| | Model Type | LoRA | |
| | Platforms | ComfyUI / RunningHub / Hugging Face | |
| | Author | RunningHub-[@四只兔子](https://www.runninghub.cn/user-center/1903712633437167617) | |
| | Original | https://www.runninghub.cn/model/public/2094270900408512514 | |
| | Try online | [https://www.runninghub.ai](https://www.runninghub.ai?utm_source=huggingface&utm_medium=basic_info&utm_campaign=model_upload&utm_content=rh-2094270900408512514) | |
| | | [https://www.runninghub.cn/runninghub-api-doc-en/](https://www.runninghub.cn/runninghub-api-doc-en/?utm_source=huggingface&utm_medium=basic_info&utm_campaign=api_doc&utm_content=rh-2094270900408512514) | |
|
|
| ## About this model |
|
|
| <h3>通用动作连续性修复 LoRA</h3><h3><p><strong>This is a general-purpose motion support LoRA, not a combat-only LoRA. It can be used for running / sports / dance / acrobatics / character interaction / combat / weapon motion and other dynamic scenes.</strong><br/><strong>这是一个通用动态辅助 LoRA，并不是战斗专用模型，可用于跑步 / 体育 / 舞蹈 / 翻滚跳跃 / 人物互动 / 战斗 / 武器动作等动态场景。</strong></p></h3><h2>Recommended Usage / 推荐使用</h2><h3><p><strong>Standalone use: around </strong><code>0.9</code><strong> is currently recommended.</strong><br/><strong>单独使用时，目前推荐权重约为 </strong><code>0.9</code><strong>。</strong></p><p>When used alone, Motion Continuity Repair needs a relatively high weight to produce a clear effect on motion continuity / slow-motion tendency / missing transitions / prompt-following.<br/>单独使用时，需要相对较高的权重，才能比较明显地影响动作连续性 / 慢动作倾向 / 动作断链 / 提示词遵循度。</p><p><a href="https://civitai.red/models/2853878/minimax-h3-combat-base-fight-motion-impact-drama-booster"><strong>With a Combat LoRA: Stage 1 around </strong></a><code>0.5–0.7</code><a href="https://civitai.red/models/2853878/minimax-h3-combat-base-fight-motion-impact-drama-booster"><strong> is recommended.</strong><br/><strong>搭配 Combat LoRA 时，一采推荐约 </strong></a><code>0.5–0.7</code><a href="https://civitai.red/models/2853878/minimax-h3-combat-base-fight-motion-impact-drama-booster"><strong>。</strong></a></p><p>Because Combat already provides strong motion speed and impact, Motion Continuity Repair only needs a medium weight to correct continuity / coordination / action logic without unnecessarily taking over the motion.<br/>因为 Combat 已经提供了较强的动作速度和打击感，此时 Motion Continuity Repair 只需要中等权重来修正动作衔接 / 协调性 / 动作逻辑，避免过度接管整个动态。</p><p>More complex sequences can gradually increase the Stage 1 weight, but very high weights may begin to reshape the entire motion logic / affect visual style / or alter audio characteristics.<br/>动作越复杂可以逐渐提高一采权重，但过高时可能开始重构整段动作逻辑 / 改变画面表现 / 影响声音特征。</p><p><strong>Stage 2: around </strong><code>0.2–0.3</code><strong> is recommended.</strong><br/><strong>二采建议约 </strong><code>0.2–0.3</code><strong>。</strong></p><p>Higher Stage 2 weights may over-stabilize the sequence and reduce motion intensity / speed / impact.<br/>二采权重过高可能会把动作收得太稳，从而削弱动作幅度 / 速度感 / 冲击力。</p><p>最简单地说就是：</p><blockquote><p><strong>单独使用：≈0.9 / 搭配 Combat：0.5–0.7 / 二采：0.2–0.3</strong></p></blockquote><p>这个才是目前测试出来的正确推荐方式。</p><p><strong>Although it is a general-purpose LoRA, it works especially well together with a Combat LoRA. Combat provides speed and impact / Motion Continuity Repair focuses on continuity, coordination, prompt-following and interaction logic.</strong><br/><strong>虽然它是一个通用 LoRA，但目前非常推荐与 Combat LoRA 搭配使用。Combat 负责速度与打击感 / Motion Continuity Repair 负责动作衔接、协调性、提示词遵循与交互逻辑。</strong></p></h3> |
|
|
| This repository provides **rh-lora** weight files. You can load them on RunningHub. |
|
|
| Finetuned from: minimax-h3 |
|
|
| ## Files |
|
|
| | File | Size | Purpose | |
| |---|---:|---| |
| | `Motion_Repair.safetensors` | 148 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](https://www.runninghub.ai/call-api/api-detail/2133100000000700025?utm_source=huggingface&utm_medium=related_links&utm_campaign=api_promotion&utm_content=rh-2094270900408512514) |
|
|
| - 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/2094270900408512514 |
| - Author page: https://www.runninghub.cn/user-center/1903712633437167617 |
|
|
|
|
