--- tags: - comfyui - lora pipeline_tag: image-text-to-image --- # rh-v4-lora [![中文](https://img.shields.io/badge/%E4%B8%AD%E6%96%87-README-555)](README_cn.md) [![RunningHub API](https://img.shields.io/badge/RunningHub-API-10B981)](https://www.runninghub.ai/call-api?utm_source=huggingface&utm_medium=badge&utm_campaign=api_promotion&utm_content=rh-1965734175850561538) [![RunningHub International](https://img.shields.io/badge/RunningHub-International-7B61FF)](https://www.runninghub.ai?utm_source=huggingface&utm_medium=badge&utm_campaign=model_upload&utm_content=rh-1965734175850561538) [![RunningHub China](https://img.shields.io/badge/RunningHub-China-2F80ED)](https://www.runninghub.cn?utm_source=huggingface&utm_medium=badge&utm_campaign=model_upload&utm_content=rh-1965734175850561538) ## Description | Field | Content | |---|---| | Model Name | rh-v4-lora | | Model Type | LoRA (image edit) | | Platforms | ComfyUI / RunningHub / Hugging Face | | Author | RunningHub-[@冰爷老杨](https://www.runninghub.ai/user-center/1958536513988550658) | | Original | https://www.runninghub.ai/model/public/1965734175850561538 | | Try online | [https://www.runninghub.ai](https://www.runninghub.ai?utm_source=huggingface&utm_medium=basic_info&utm_campaign=model_upload&utm_content=rh-1965734175850561538) | | | [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-1965734175850561538) | ## About this model

Stable blending images (deeper training), short trigger words (reducing the impact on tag comprehension), light and shadow understanding more in line with real physics (trained with a large amount of C4D high-definition rendering materials, I worked my butt off for half a month and even made my 5090 render until it smoked!), can stably blend high-difficulty transparent subjects, can blend high-difficulty frosted mirrors or water surfaces (capable of creating reflection effects closely attached to the subject), full lora (more stable, but also higher training cost).


Trigger words: Make it blend into the background (the complete trigger words used for training)

Or: Make it blend also works, as testing found it effective


Beginners are recommended to use the blending workflow I uploaded


Open source! Open source! Open source! Emphasizing this important matter three times! Free download! If you use it secretly without liking it, can your conscience handle it???

This repository provides **rh-v4-lora** weight files. You can load them on RunningHub. Finetuned from: Flux1-Kontext **Trigger words:** Make it blend into the background ## Files | File | Size | Purpose | |---|---:|---| | `冰爷老杨真实溶图V4.safetensors` | 164 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-1965734175850561538) - 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.ai/model/public/1965734175850561538 - Author page: https://www.runninghub.ai/user-center/1958536513988550658