Update README.md

.gitattributes

@@ -1,38 +1,81 @@
 *.7z filter=lfs diff=lfs merge=lfs -text
 *.arrow filter=lfs diff=lfs merge=lfs -text
 *.bin filter=lfs diff=lfs merge=lfs -text
-*.bin.* filter=lfs diff=lfs merge=lfs -text
 *.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
 *.ftz filter=lfs diff=lfs merge=lfs -text
 *.gz filter=lfs diff=lfs merge=lfs -text
 *.h5 filter=lfs diff=lfs merge=lfs -text
 *.joblib filter=lfs diff=lfs merge=lfs -text
 *.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
 *.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
 *.onnx filter=lfs diff=lfs merge=lfs -text
 *.ot filter=lfs diff=lfs merge=lfs -text
 *.parquet filter=lfs diff=lfs merge=lfs -text
 *.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
 *.pt filter=lfs diff=lfs merge=lfs -text
 *.pth filter=lfs diff=lfs merge=lfs -text
 *.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
 saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
 *.tflite filter=lfs diff=lfs merge=lfs -text
 *.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
 *.xz filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
-*.zstandard filter=lfs diff=lfs merge=lfs -text
-*.tfevents* filter=lfs diff=lfs merge=lfs -text
-*.db* filter=lfs diff=lfs merge=lfs -text
-*.ark* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*data* filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.meta filter=lfs diff=lfs merge=lfs -text
-**/*ckpt*.index filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.gguf* filter=lfs diff=lfs merge=lfs -text
-*.ggml filter=lfs diff=lfs merge=lfs -text
-*.llamafile* filter=lfs diff=lfs merge=lfs -text
-*.pt2 filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+images/overflow.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/1.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/10.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/11.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/12.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/14.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/15.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/16.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/17.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/18.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/19.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/2.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/21.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/22.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/23.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/24.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/26.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/27.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/28.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/29.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/3.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/30.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/31.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/32.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/34.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/35.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/36.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/38.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/39.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/4.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/40.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/41.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/42.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/43.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/44.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/45.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/46.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/47.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/48.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/49.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/50.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/6.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/7.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/8.png filter=lfs diff=lfs merge=lfs -text
+images/show_case/9.png filter=lfs diff=lfs merge=lfs -text
+diffusion_pytorch_model.safetensors filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,47 +1,187 @@
 ---
-license: Apache License 2.0
-
-#model-type:
-##如 gpt、phi、llama、chatglm、baichuan 等
-#- gpt
-
-#domain:
-##如 nlp、cv、audio、multi-modal
-#- nlp
-
-#language:
-##语言代码列表 https://help.aliyun.com/document_detail/215387.html?spm=a2c4g.11186623.0.0.9f8d7467kni6Aa
-#- cn 
-
-#metrics:
-##如 CIDEr、Blue、ROUGE 等
-#- CIDEr
-
-#tags:
-##各种自定义，包括 pretrained、fine-tuned、instruction-tuned、RL-tuned 等训练方法和其他
-#- pretrained
-
-#tools:
-##如 vllm、fastchat、llamacpp、AdaSeq 等
-#- vllm
+license: apache-2.0
 ---
-### 当前模型的贡献者未提供更加详细的模型介绍。模型文件和权重，可浏览“模型文件”页面获取。
-#### 您可以通过如下git clone命令，或者ModelScope SDK来下载模型
+<div style="display: flex; justify-content: center; align-items: center;">
+  <img src="./images/images_alibaba.png" alt="alibaba" style="width: 20%; height: auto; margin-right: 5%;">
+  <img src="./images/images_alimama.png" alt="alimama" style="width: 20%; height: auto;">
+</div>
 
-SDK下载
-```bash
-#安装ModelScope
-pip install modelscope
-```
-```python
-#SDK模型下载
-from modelscope import snapshot_download
-model_dir = snapshot_download('alimama-creative/SDXL-EcomID')
-```
-Git下载
-```
-#Git模型下载
-git clone https://www.modelscope.cn/alimama-creative/SDXL-EcomID.git
-```
+[中文版Readme](./README_ZH.md)
 
-<p style="color: lightgrey;">如果您是本模型的贡献者，我们邀请您根据<a href="https://modelscope.cn/docs/ModelScope%E6%A8%A1%E5%9E%8B%E6%8E%A5%E5%85%A5%E6%B5%81%E7%A8%8B%E6%A6%82%E8%A7%88" style="color: lightgrey; text-decoration: underline;">模型贡献文档</a>，及时完善模型卡片内容。</p>
+EcomID aims to generate customized images from a single reference ID image, ensuring strong semantic consistency while being controlled by keypoints.
+
+This repository provides the EcomID method and model, combining the strengths of [PuLID](https://github.com/ToTheBeginning/PuLID) and [InstantID](https://github.com/instantX-research/InstantID) for better background consistency, facial keypoint control, and realistic facial representation with improved similarity.
+
+# EcomID Overview
+
+## EcomID Structure
+  <img src="./images/overflow.png" alt="alibaba" style="width: 100%; height: auto; margin-right: 5%;">
+
+
+- **IP-Adapter of PuLID**: EcomID incorporates the ID-Encoder and cross-attention components from PuLID, trained with alignment loss. 
+This method effectively reduces the interference of ID embeddings on text embeddings within the cross-attention part, minimizing disruption to the underlying model's text-to-image capabilities.
+- **InstantID’s IdentityNet Architecture**: Utilizing **a dataset of 2 million aesthetically pleasing portrait images**, IdentityNet enhances keypoint control, improving ID consistency and facial realism. During training, the IP-adapter is frozen, and only the IdentityNet is trained. Facial landmarks are used as conditional inputs, while face embeddings are integrated into IdentityNet via cross-attention.
+
+# Show Cases
+## Comparison with Other Methods
+### 1、Preserved Text-to-Image Capability
+
+<table>
+    <tr>
+        <th style="width: 28%;">Prompt</th>
+        <th style="width: 24%;">Reference Image</th>
+        <th style="width: 24%;">EcomID</th>
+        <th style="width: 24%;">InstantID</th>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">girl, white skin, black hair, long wavy hair, <span style="color:red"><strong>in European style living room, Retro tone, decorations</strong></span>, depth of field.</td>
+        <td><img src="images/show_case/50.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/49.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/48.png" alt="InstantID图像" width="100%"></td>
+    </tr>
+<table>
+
+As shown above, EcomID ***preserves background generation abilities while minimizing stylization, greatly enhancing realism***. 
+The visualizations highlight more authentic portraits with improved background semantic consistency, showcasing EcomID's advantage in generating realistic images.
+
+### 2、Improved Facial Control and Consistency
+<table>
+    <tr>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 19%;">Reference Image</th>
+        <th style="width: 19%;">EcomID</th>
+        <th style="width: 19%;">InstantID</th>
+        <th style="width: 19%;">PuLID</th>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A close-up portrait of a man standing in the library, holding <span style="color:red"><strong>two smiling toddlers</strong></span> next to him.</td>
+        <td><img src="images/show_case/20.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/17.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/18.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/19.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+<table>
+
+As shown above, EcomID employs keypoints as conditional inputs for training, ***allowing for precise adjustments of facial positions, sizes, and orientations***. This capability ensures that the generated portraits are more controllable while further enhancing facial similarity and the overall quality of the images.
+
+### More showcases
+EcomID enhances portrait representation, delivering a more authentic and aesthetically pleasing appearance while ensuring semantic consistency and greater internal ID similarity (i.e., traits that do not vary with age, hairstyle, glasses, or other physical changes).
+
+<table>
+    <tr>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 19%;">Reference Image</th>
+        <th style="width: 19%;">EcomID</th>
+        <th style="width: 19%;">InstantID</th>
+        <th style="width: 19%;">PuLID</th>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A close-up portrait of a <span style="color:red"><strong>little girl with double braids</strong></span>, wearing a white dress, standing on the beach during sunset.</td>
+        <td><img src="images/show_case/21.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/22.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/23.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/24.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A close-up portrait of a <span style="color:red"><strong>very little girl</strong></span> with double braids, wearing <span style="color:red"><strong>a hat</strong></span> and white dress, standing on the beach during sunset.</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/47.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/46.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/45.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">Agrizzled detective, <span style="color:red"><strong>fedora</strong></span> casting a shadow over his square jaw, a <span style="color:red"><strong>cigar dangling from his lips</strong></span>, his trench coat evocative of film noir, in a <span style="color:red"><strong>rainy alley</strong></span>.</td>
+        <td><img src="images/show_case/25.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/26.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/27.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/28.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A smiling girl with <span style="color:red"><strong>bangs and long hair</strong></span> in a school uniform stands under cherry trees, holding a book.</td>
+        <td><img src="images/show_case/29.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/30.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/31.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/32.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A <span style="color:red"><strong>very old</strong></span> witch, wearing a black cloak, with a pointed hat, holding a magic wand, against a background of a misty forest.</td>
+        <td><img src="images/show_case/33.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/34.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/35.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/36.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td style="font-size: 12px;">A man clad in cyberpunk fashion: <span style="color:red"><strong>neon accents, reflective sunglasses，</strong></span> and a leather jacket with glowing circuit patterns. He stands stoically amidst a soaked cityscape.</td>
+        <td><img src="images/show_case/37.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/38.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/39.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/40.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+
+</table>
+
+### More Base Models, Resolutions, and Styles
+<table>
+    <tr>
+        <th style="width: 12%;">SDXL models</th>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 16%;">Reference Image</th>
+        <th style="width: 16%;">EcomID</th>
+        <th style="width: 16%;">InstantID</th>
+        <th style="width: 16%;">PuLID</th>
+    </tr>
+    <tr>
+        <td>sd-xl-base-1.0</td>
+        <td style="font-size: 12px;">girl, solo, brown hair, holding a little teddy bear on her hands, wearing a school uniform, standing in the library, <span style="color:red"><strong>cartoon style</strong></span>.</td>
+        <td><img src="images/show_case/1.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/2.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/3.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/4.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>EcomXL</td>
+        <td style="font-size: 12px;">A close-up portrait of a <span style="color:red"><strong>very little girl</strong></span> with double braids, wearing <span style="color:red"><strong>a hat</strong></span> and white dress, standing on the beach during sunset.</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/47.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/46.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/45.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>DreamShaperXL</td>
+        <td style="font-size: 12px;">solo, looking_at_viewer, smile, brown_hair, upper_body, open_clothes, teeth, open_jacket, black_jacket, blurry_background, realistic</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/6.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/7.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/8.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>leosam_xl_v7</td>
+        <td style="font-size: 12px;">A close-up portrait of a girl, solo, dress, jewelry, beach and sea, pink_dress, realistic.</td>
+        <td><img src="images/show_case/9.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/15.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/14.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/16.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+</table>
+
+### Notes
+- Unless otherwise specified, the showcases are generated using the base model EcomXL, which is also highly compatible with various other SDXL-based models, such as [leosams-helloworld-xl](https://civitai.com/models/43977/leosams-helloworld-xl), [dreamshaper-xl](https://civitai.com/models/112902/dreamshaper-xl), [stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) and so on.
+- It works very well with SDXL Turbo/Lighting, [EcomXL Inpainting ControlNet](https://huggingface.co/alimama-creative/EcomXL_controlnet_inpaint) and [EcomXL Softedge ControlNet](https://huggingface.co/alimama-creative/EcomXL_controlnet_softedge).
+
+# How to use
+
+## ComfyUI
+
+- The EcomID_ComfyUI node has been released: [click here](https://github.com/alimama-creative/SDXL_EcomID_ComfyUI)
+
+# Training Details
+
+The model is trained on 2M Taobao images, where the proportion of human faces is greater than 3%. The images have a resolution greater than 800, and the aesthetic score is above 5.5.
+
+Mixed precision: fp16
+
+Learning rate: 1e-4
+
+Batch size: 2
+
+Image size: 1024x1024

README_ZH.md

@@ -0,0 +1,172 @@
+<div style="display: flex; justify-content: center; align-items: center;">
+  <img src="./images/images_alibaba.png" alt="alibaba" style="width: 20%; height: auto; margin-right: 5%;">
+  <img src="./images/images_alimama.png" alt="alimama" style="width: 20%; height: auto;">
+</div>
+EcomID 旨在从单个ID参考图像生成定制的保ID图像，优势在于很强的语义一致性，同时受人脸关键点控制。
+
+此仓库提供了 EcomID 方法和模型，方法上结合了 [PuLID](https://github.com/ToTheBeginning/PuLID) 和 [InstantID](https://github.com/instantX-research/InstantID) 的优点，以获得更好的背景一致性、面部关键点控制、更真实的面部以及更高的相似度。
+
+# EcomID 概述
+## EcomID 结构
+  <img src="./images/overflow.png" alt="alibaba" style="width: 100%; height: auto; margin-right: 5%;">
+
+- **PuLID 的 IP-Adapter**：EcomID 借鉴了 PuLID 的 ID-Encoder 和交叉注意力组件，其使用对齐损失训练而成。
+故而该方法有效减少了 ID embedding 对交叉注意力部分的文本 embedding的干扰，最小化对底层模型文本到图像能力的干扰。
+
+- **InstantID 的 IdentityNet 架构**：利用 *200 万张美观的人像图像数据集*，训练了IdentityNet，增强了关键点控制，提高了 ID 一致性和面部真实感。在训练过程中，IP-adapter 被冻结，只有 IdentityNet 被训练。面部Keypoint用作条件输入，同时面部嵌入通过交叉注意力集成到 IdentityNet 中。
+
+# 展示案例
+## 与其他方法的比较
+### 1、保留文本到图像能力
+<table>
+    <tr>
+        <th style="width: 28%;">Prompt</th>
+        <th style="width: 24%;">参考图像</th>
+        <th style="width: 24%;">EcomID</th>
+        <th style="width: 24%;">InstantID</th>
+    </tr>
+    <tr>
+        <td>女孩，白皮肤，黑头发，长卷发，<span style="color:red"><strong>在欧洲风格的客厅，复古色调，装饰品</strong></span>，景深。</td>
+        <td><img src="images/show_case/50.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/49.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/48.png" alt="InstantID图像" width="100%"></td>
+    </tr>
+<table>
+
+如上所示，EcomID ***保留了背景生成能力，同时最大限度地减少了风格化，从而大大增强了真实感***。
+如图可见，EcomID的背景语义一致性得到了改善，且在生成真实图像方面格外有优势。
+
+### 2、改善面部控制和相似度
+<table>
+    <tr>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 19%;">参考图像</th>
+        <th style="width: 19%;">EcomID</th>
+        <th style="width: 19%;">InstantID</th>
+        <th style="width: 19%;">PuLID</th>
+    </tr>
+    <tr>
+        <td>在图书馆前站着的男人的特写肖像，<span style="color:red"><strong>抱着两个微笑的幼儿</strong></span>。</td>
+        <td><img src="images/show_case/20.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/17.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/18.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/19.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+<table>
+
+如上所示，EcomID 使用关键点作为训练的条件输入，***允许精确调整面部位置、大小和方向***。这种能力确保生成的人像更加可控，同时进一步增强了面部相似性和图像的整体质量。
+
+### 更多案例
+EcomID 提高了人像表现，提供了更真实和美观的外观，同时确保语义一致性和更好的内部 ID 相似性（即，不随年龄、发型、眼镜或其他身体变化而变化的特征）。
+<table>
+    <tr>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 19%;">参考图像</th>
+        <th style="width: 19%;">EcomID</th>
+        <th style="width: 19%;">InstantID</th>
+        <th style="width: 19%;">PuLID</th>
+    </tr>
+    <tr>
+        <td>一个<span style="color:red"><strong>双辫小女孩</strong></span>的特写肖像，穿着白色裙子，傍晚在海滩上。</td>
+        <td><img src="images/show_case/21.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/22.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/23.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/24.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>一个<span style="color:red"><strong>非常小的女孩</strong></span>，双辫，带着<spann style="color:red"><strong>帽子</strong></span>和白色裙子，傍晚在海滩上。</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/47.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/46.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/45.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>一个满脸胡茬的侦探，<span style="color:red"><strong>戴着帽子</strong></span>，阴影投在他方形的下巴上，<span style="color:red"><strong>嘴里叼着一根香烟</strong></span>，他的风衣唤起了电影黑色风格，在一个<span style="color:red"><strong>阴雨小巷</strong></span>里。</td>
+        <td><img src="images/show_case/25.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/26.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/27.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/28.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>一个微笑的女孩，<span style="color:red"><strong>齐刘海和长发</strong></span>，穿着校服，站在樱花树下，手里拿着一本书。</td>
+        <td><img src="images/show_case/29.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/30.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/31.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/32.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>一个<spann style="color:red"><strong>非常老的</strong></span>女巫，穿着黑色斗篷，戴着尖顶帽，手握魔杖，在雾气缭绕的森林背景下。</td>
+        <td><img src="images/show_case/33.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/34.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/35.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/36.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>一个身穿赛博朋克风格的男人：<span style="color:red"><strong>霓虹配件，反光太阳镜，</strong></span>和带有发光电路图案的皮夹克。他在湿润的城市风貌中冷静地站着。</td>
+        <td><img src="images/show_case/37.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/38.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/39.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/40.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+</table>
+
+### 更多基础模型、分辨率和风格
+<table>
+    <tr>
+        <th style="width: 12%;">SDXL 模型</th>
+        <th style="width: 24%;">Prompt</th>
+        <th style="width: 16%;">参考图像</th>
+        <th style="width: 16%;">EcomID</th>
+        <th style="width: 16%;">InstantID</th>
+        <th style="width: 16%;">PuLID</th>
+    </tr>
+    <tr>
+        <td>sd-xl-base-1.0</td>
+        <td>女孩，单独，棕色头发，手里抱着一个小泰迪熊，穿着校服，站在图书馆里，<span style="color:red"><strong>卡通风格</strong></span>。</td>
+        <td><img src="images/show_case/1.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/2.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/3.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/4.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>EcomXL</td>
+        <td>一个<span style="color:red"><strong>非常小的女孩</strong></span>的特写肖像，双辫，带着<spann style="color:red"><strong>帽子</strong></span>和白色裙子，傍晚在海滩上。</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/47.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/46.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/45.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>DreamShaperXL</td>
+        <td>单独，面向观众，微笑，棕色头发，上半身，开衫，牙齿，打开的外套，黑色夹克，模糊背景，真实感</td>
+        <td><img src="images/show_case/44.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/6.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/7.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/8.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+    <tr>
+        <td>leosam_xl_v7</td>
+        <td>一个特写肖像，女孩，单独，裙子，珠宝，海滩和大海，粉色裙子，真实感。</td>
+        <td><img src="images/show_case/9.png" alt="参考图像" width="100%"></td>
+        <td><img src="images/show_case/15.png" alt="EcomID图像" width="100%"></td>
+        <td><img src="images/show_case/14.png" alt="InstantID图像" width="100%"></td>
+        <td><img src="images/show_case/16.png" alt="PuLID图像" width="100%"></td>
+    </tr>
+</table>
+
+### 注意事项
+- 除非特别说明，大部分展示案例使用基础模型 EcomXL 生成；同时EcomID与其他基于 SDXL 的模型也高度兼容，例如 [leosams-helloworld-xl](https://civitai.com/models/43977/leosams-helloworld-xl)、[dreamshaper-xl](https://civitai.com/models/112902/dreamshaper-xl)、[stable-diffusion-xl-base-1.0](https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0) 等。
+- 它与 SDXL Turbo/Lighting、[EcomXL Inpainting ControlNet](https://huggingface.co/alimama-creative/EcomXL_controlnet_inpaint) 和 [EcomXL Softedge ControlNet](https://huggingface.co/alimama-creative/EcomXL_controlnet_softedge) 的兼容性非常好。
+# 如何使用
+## ComfyUI
+- 已发布 EcomID_ComfyUI 节点：[点击这里](https://github.com/alimama-creative/SDXL_EcomID_ComfyUI)
+# 训练细节
+该模型在 200 万张淘宝图像上进行训练，其中人脸比例大于 3%。图像分辨率大于800，且美学评分超过 5.5。
+
+混合精度：fp16
+
+学习率：1e-4
+
+批量大小：2
+
+图像大小：1024x1024

configuration.json

@@ -0,0 +1 @@
+{"framework": "pytorch", "task": "others", "allow_remote": true}

workflows/ecomid_basic_workflow.json

@@ -0,0 +1,800 @@
+{
+  "last_node_id": 15,
+  "last_link_id": 18,
+  "nodes": [
+    {
+      "id": 1,
+      "type": "InstantIDModelLoader",
+      "pos": [
+        1009.44140625,
+        227.6875
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 0,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "INSTANTID",
+          "type": "INSTANTID",
+          "links": [
+            3
+          ],
+          "shape": 3,
+          "label": "INSTANTID",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "InstantIDModelLoader"
+      },
+      "widgets_values": [
+        "ip-adapter.bin"
+      ]
+    },
+    {
+      "id": 9,
+      "type": "EcomID_PulidModelLoader",
+      "pos": [
+        999,
+        320
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 1,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "PULID",
+          "type": "PULID",
+          "links": [
+            4
+          ],
+          "shape": 3,
+          "label": "PULID",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EcomID_PulidModelLoader"
+      },
+      "widgets_values": [
+        "ip-adapter_pulid_sdxl_fp16.safetensors"
+      ]
+    },
+    {
+      "id": 3,
+      "type": "PulidEvaClipLoader",
+      "pos": [
+        1101,
+        421
+      ],
+      "size": {
+        "0": 210,
+        "1": 26
+      },
+      "flags": {},
+      "order": 2,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "EVA_CLIP",
+          "type": "EVA_CLIP",
+          "links": [
+            5
+          ],
+          "shape": 3,
+          "label": "EVA_CLIP",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PulidEvaClipLoader"
+      }
+    },
+    {
+      "id": 10,
+      "type": "EcomIDFaceAnalysis",
+      "pos": [
+        999,
+        488
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 3,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "FACEANALYSIS",
+          "type": "FACEANALYSIS",
+          "links": [
+            6
+          ],
+          "shape": 3,
+          "label": "FACEANALYSIS",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EcomIDFaceAnalysis"
+      },
+      "widgets_values": [
+        "CPU"
+      ]
+    },
+    {
+      "id": 2,
+      "type": "ControlNetLoader",
+      "pos": [
+        999,
+        589
+      ],
+      "size": {
+        "0": 315,
+        "1": 58
+      },
+      "flags": {},
+      "order": 4,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "CONTROL_NET",
+          "type": "CONTROL_NET",
+          "links": [
+            7
+          ],
+          "shape": 3,
+          "label": "CONTROL_NET",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ControlNetLoader"
+      },
+      "widgets_values": [
+        "yinu_instantid.safetensors"
+      ]
+    },
+    {
+      "id": 5,
+      "type": "CLIPTextEncode",
+      "pos": [
+        975,
+        689
+      ],
+      "size": {
+        "0": 380,
+        "1": 160
+      },
+      "flags": {},
+      "order": 8,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 1,
+          "label": "clip"
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            9
+          ],
+          "slot_index": 0,
+          "label": "CONDITIONING"
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "1girl, solo, dress, jewelry, beach, pink_dress, realistic"
+      ]
+    },
+    {
+      "id": 6,
+      "type": "CLIPTextEncode",
+      "pos": [
+        975,
+        893
+      ],
+      "size": {
+        "0": 380,
+        "1": 160
+      },
+      "flags": {},
+      "order": 9,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "clip",
+          "type": "CLIP",
+          "link": 2,
+          "label": "clip"
+        }
+      ],
+      "outputs": [
+        {
+          "name": "CONDITIONING",
+          "type": "CONDITIONING",
+          "links": [
+            10
+          ],
+          "slot_index": 0,
+          "label": "CONDITIONING"
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CLIPTextEncode"
+      },
+      "widgets_values": [
+        "bad hand, (worst quality, low quality, nevus, normal quality:1.6), blur skin,nevus,signature, logo, watermark,username,text"
+      ]
+    },
+    {
+      "id": 13,
+      "type": "VAEDecode",
+      "pos": [
+        2113,
+        437
+      ],
+      "size": {
+        "0": 210,
+        "1": 46
+      },
+      "flags": {},
+      "order": 12,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "samples",
+          "type": "LATENT",
+          "link": 14,
+          "label": "samples"
+        },
+        {
+          "name": "vae",
+          "type": "VAE",
+          "link": 15,
+          "label": "vae"
+        }
+      ],
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            16
+          ],
+          "shape": 3,
+          "label": "IMAGE",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "VAEDecode"
+      }
+    },
+    {
+      "id": 8,
+      "type": "ApplyEcomIDAdvanced",
+      "pos": [
+        1411,
+        437
+      ],
+      "size": {
+        "0": 315,
+        "1": 402
+      },
+      "flags": {},
+      "order": 10,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "instantid_ipa",
+          "type": "INSTANTID",
+          "link": 3,
+          "label": "instantid_ipa"
+        },
+        {
+          "name": "pulid",
+          "type": "PULID",
+          "link": 4,
+          "label": "pulid"
+        },
+        {
+          "name": "eva_clip",
+          "type": "EVA_CLIP",
+          "link": 5,
+          "label": "eva_clip"
+        },
+        {
+          "name": "insightface",
+          "type": "FACEANALYSIS",
+          "link": 6,
+          "label": "insightface"
+        },
+        {
+          "name": "control_net",
+          "type": "CONTROL_NET",
+          "link": 7,
+          "label": "control_net"
+        },
+        {
+          "name": "image",
+          "type": "IMAGE",
+          "link": 8,
+          "label": "image"
+        },
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 17,
+          "label": "model"
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 9,
+          "label": "positive"
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 10,
+          "label": "negative"
+        },
+        {
+          "name": "image_kps",
+          "type": "IMAGE",
+          "link": null,
+          "label": "image_kps"
+        },
+        {
+          "name": "mask",
+          "type": "MASK",
+          "link": null,
+          "label": "mask"
+        }
+      ],
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            11
+          ],
+          "shape": 3,
+          "label": "MODEL",
+          "slot_index": 0
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "links": [
+            12
+          ],
+          "shape": 3,
+          "label": "positive",
+          "slot_index": 1
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "links": [
+            13
+          ],
+          "shape": 3,
+          "label": "negative",
+          "slot_index": 2
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "ApplyEcomIDAdvanced"
+      },
+      "widgets_values": [
+        "fidelity",
+        0,
+        1,
+        0.3,
+        0.8,
+        0,
+        "average"
+      ]
+    },
+    {
+      "id": 15,
+      "type": "EmptyLatentImage",
+      "pos": [
+        1407,
+        902
+      ],
+      "size": {
+        "0": 315,
+        "1": 106
+      },
+      "flags": {},
+      "order": 5,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            18
+          ],
+          "shape": 3,
+          "label": "LATENT",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "EmptyLatentImage"
+      },
+      "widgets_values": [
+        1024,
+        1024,
+        1
+      ]
+    },
+    {
+      "id": 11,
+      "type": "LoadImage",
+      "pos": [
+        573,
+        329
+      ],
+      "size": [
+        315,
+        314
+      ],
+      "flags": {},
+      "order": 6,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "IMAGE",
+          "type": "IMAGE",
+          "links": [
+            8
+          ],
+          "shape": 3,
+          "label": "IMAGE",
+          "slot_index": 0
+        },
+        {
+          "name": "MASK",
+          "type": "MASK",
+          "links": null,
+          "shape": 3,
+          "label": "MASK"
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "LoadImage"
+      },
+      "widgets_values": [
+        "4 (2).png",
+        "image"
+      ]
+    },
+    {
+      "id": 4,
+      "type": "CheckpointLoaderSimple",
+      "pos": [
+        564,
+        739
+      ],
+      "size": {
+        "0": 315,
+        "1": 98
+      },
+      "flags": {},
+      "order": 7,
+      "mode": 0,
+      "outputs": [
+        {
+          "name": "MODEL",
+          "type": "MODEL",
+          "links": [
+            17
+          ],
+          "slot_index": 0,
+          "label": "MODEL"
+        },
+        {
+          "name": "CLIP",
+          "type": "CLIP",
+          "links": [
+            1,
+            2
+          ],
+          "slot_index": 1,
+          "label": "CLIP"
+        },
+        {
+          "name": "VAE",
+          "type": "VAE",
+          "links": [
+            15
+          ],
+          "slot_index": 2,
+          "label": "VAE"
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "CheckpointLoaderSimple"
+      },
+      "widgets_values": [
+        "ecomxl.safetensors"
+      ]
+    },
+    {
+      "id": 12,
+      "type": "KSampler",
+      "pos": [
+        1763,
+        436
+      ],
+      "size": {
+        "0": 315,
+        "1": 262
+      },
+      "flags": {},
+      "order": 11,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "model",
+          "type": "MODEL",
+          "link": 11,
+          "label": "model"
+        },
+        {
+          "name": "positive",
+          "type": "CONDITIONING",
+          "link": 12,
+          "label": "positive"
+        },
+        {
+          "name": "negative",
+          "type": "CONDITIONING",
+          "link": 13,
+          "label": "negative"
+        },
+        {
+          "name": "latent_image",
+          "type": "LATENT",
+          "link": 18,
+          "label": "latent_image"
+        }
+      ],
+      "outputs": [
+        {
+          "name": "LATENT",
+          "type": "LATENT",
+          "links": [
+            14
+          ],
+          "shape": 3,
+          "label": "LATENT",
+          "slot_index": 0
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "KSampler"
+      },
+      "widgets_values": [
+        730401293336759,
+        "randomize",
+        25,
+        3.5,
+        "dpm_2",
+        "karras",
+        1
+      ]
+    },
+    {
+      "id": 14,
+      "type": "PreviewImage",
+      "pos": [
+        2110,
+        532
+      ],
+      "size": [
+        428.19834675017046,
+        539.6653026265071
+      ],
+      "flags": {},
+      "order": 13,
+      "mode": 0,
+      "inputs": [
+        {
+          "name": "images",
+          "type": "IMAGE",
+          "link": 16,
+          "label": "images"
+        }
+      ],
+      "properties": {
+        "Node name for S&R": "PreviewImage"
+      },
+      "widgets_values": [
+        "0",
+        "0",
+        "0"
+      ]
+    }
+  ],
+  "links": [
+    [
+      1,
+      4,
+      1,
+      5,
+      0,
+      "CLIP"
+    ],
+    [
+      2,
+      4,
+      1,
+      6,
+      0,
+      "CLIP"
+    ],
+    [
+      3,
+      1,
+      0,
+      8,
+      0,
+      "INSTANTID"
+    ],
+    [
+      4,
+      9,
+      0,
+      8,
+      1,
+      "PULID"
+    ],
+    [
+      5,
+      3,
+      0,
+      8,
+      2,
+      "EVA_CLIP"
+    ],
+    [
+      6,
+      10,
+      0,
+      8,
+      3,
+      "FACEANALYSIS"
+    ],
+    [
+      7,
+      2,
+      0,
+      8,
+      4,
+      "CONTROL_NET"
+    ],
+    [
+      8,
+      11,
+      0,
+      8,
+      5,
+      "IMAGE"
+    ],
+    [
+      9,
+      5,
+      0,
+      8,
+      7,
+      "CONDITIONING"
+    ],
+    [
+      10,
+      6,
+      0,
+      8,
+      8,
+      "CONDITIONING"
+    ],
+    [
+      11,
+      8,
+      0,
+      12,
+      0,
+      "MODEL"
+    ],
+    [
+      12,
+      8,
+      1,
+      12,
+      1,
+      "CONDITIONING"
+    ],
+    [
+      13,
+      8,
+      2,
+      12,
+      2,
+      "CONDITIONING"
+    ],
+    [
+      14,
+      12,
+      0,
+      13,
+      0,
+      "LATENT"
+    ],
+    [
+      15,
+      4,
+      2,
+      13,
+      1,
+      "VAE"
+    ],
+    [
+      16,
+      13,
+      0,
+      14,
+      0,
+      "IMAGE"
+    ],
+    [
+      17,
+      4,
+      0,
+      8,
+      6,
+      "MODEL"
+    ],
+    [
+      18,
+      15,
+      0,
+      12,
+      3,
+      "LATENT"
+    ]
+  ],
+  "groups": [],
+  "config": {},
+  "extra": {
+    "ds": {
+      "scale": 0.6830134553650709,
+      "offset": [
+        -260.1114479220462,
+        -82.98489012650744
+      ]
+    }
+  },
+  "version": 0.4
+}