---
title: SimpleSDXL-models
canonical_url: "https://www.modelscope.cn/models/metercai/SimpleSDXL-models"
md_url: "https://www.modelscope.cn/models/metercai/SimpleSDXL-models.md"
repository: metercai/SimpleSDXL-models
last_updated: 2025-06-15
license: "Apache License 2.0"
pipeline_tag: text-to-image-synthesis
tasks:
  - text-to-image-synthesis
  - image-to-image
parameters: 19.7B
tensor_type:
  - F32
  - I64
  - BF16
  - F16
library_name:
  - safetensors
downloads: 2038
stars: 8
---

# SimpleSDXL-models

> SimpleSDXL-models - metercai 在 ModelScope 开源的模型。SimpleSDXL 在Fooocus基础上增强功能，可无缝迁移升级 Enhanced features base on Fooocus, can be seamless upgrading

metercai/SimpleSDXL-models 是 ModelScope 魔搭社区上的 19.7B 参数text-to-image-synthesis、image-to-image模型，采用 Apache License 2.0 许可。

- **Repository**: metercai/SimpleSDXL-models
- **License**: Apache License 2.0
- **Tasks**: text-to-image-synthesis, image-to-image
- **Parameters**: 19.7B
- **Downloads**: 2038
- **Stars**: 8
- **Last updated**: 2025-06-15

Source: https://www.modelscope.cn/models/metercai/SimpleSDXL-models

---

## SimpleSDXL
<div align=center><img src="https://github.com/metercai/SimpleSDXL/assets/5652458/661820e0-0899-406e-aa8e-1c4f541943e3"></div>
在Fooocus基础上增强功能，可无缝迁移升级 <br> Enhanced features base on Fooocus, can be seamless upgrading

- **中英文混编提示词**: 离线模型，无API依赖和限制。<br>
  **Chinese English mixed prompts**:  Offline model without API dependencies and limitations.
- **已生成图片集浏览**: 原生版本仅限浏览当次生成的图片集。 <br>  **Finished image sets browsing**:  Fooocus only can browse the current generated image set.
- **查看生成参数和提取重生**: 可即时查看历史图片的生成参数，也可提取参数回填界面，二次生成。 <br>  **View parameters and extract regeneration**:  Can view the generation parameters of historical images, and can also extract parameters to backfill for secondary generation.
- **在线切换预置包和背景色**: 原生版本需要修改启动参数重启。 <br>  **Switch preset and theme online**:  Fooocus requires modification of startup parameters to restart.

## 安装方法
在SimpleSDXL目录下同步本项目所有目录和文件，并改名为models

    # 1，下载应用代码库
    git clone https://github.com/metercai/SimpleSDXL
    cd SimpleSDXL
    # 2，安装模型文件，需要提前安装lfs模块
    git clone https://www.modelscope.cn/metercai/SimpleSDXL-models.git models

SimpleSDXL的具体使用，参见：https://github.com/metercai/SimpleSDXL 

## 模型清单
本模型库包含了SDXL出图中需要的各种模型，具体包括：

基础模型：
- sd_xl_base_1.0_0.9vae.safetensors
- bluePencilXL_v050.safetensors
- juggernautXL_version6Rundiffusion.safetensors
- realisticStockPhoto_v10.safetensors

精炼模型：
- sd_xl_refiner_1.0_0.9vae.safetensors
- DreamShaper_8_pruned.safetensors

LoRa模型：
- sd_xl_offset_example-lora_1.0.safetensors
- SDXL_FILM_PHOTOGRAPHY_STYLE_BetaV0.4.safetensors
- sdxl_lcm_lora.safetensors

Embeddings模型：
- unaestheticXLv31.safetensors

Inpaint修复模型：
- fooocus_inpaint_head.pth
- inpaint_v26.fooocus.patch

Controlnet模型：
- control-lora-canny-rank128.safetensors
- fooocus_xl_cpds_128.safetensors
- fooocus_ip_negative.safetensors
- ip-adapter-plus_sdxl_vit-h.bin
- ip-adapter-plus-face_sdxl_vit-h.bin
- detection_Resnet50_Final.pth
- parsing_parsenet.pth

Clip_vision模型：
- clip_vision_vit_h.safetensors

Upscale模型：
- fooocus_upscaler_s409985e5.bin

Prompt_expansion模型：
- fooocus_expansion

Translator翻译模型：
- nllb-200-distilled-600M

总计43G文件，用git-lfs进行管理包含隐含目录，需占用本地86G硬盘空间。