Add files using upload-large-folder tool

.gitattributes

@@ -1,35 +1,35 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow 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
-*.zst filter=lfs diff=lfs merge=lfs -text
-*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow 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
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,141 @@
+---
+license: apache-2.0
+---
+<h1 align='center'>EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation</h1>
+
+<div align='center'>
+    <a href='https://github.com/mengrang' target='_blank'>Rang Meng</a><sup>1</sup>&emsp;
+    <a href='https://github.com/' target='_blank'>Yan Wang</a>&emsp;
+    <a href='https://github.com/' target='_blank'>Weipeng Wu</a>&emsp;
+    <a href='https://github.com/' target='_blank'>Ruobing Zheng</a>&emsp;
+    <a href='https://lymhust.github.io/' target='_blank'>Yuming Li</a><sup>2</sup>&emsp;
+    <a href='https://openreview.net/profile?id=~Chenguang_Ma3' target='_blank'>Chenguang Ma</a><sup>2</sup>
+</div>
+<div align='center'>
+Terminal Technology Department, Alipay, Ant Group.
+</div>
+<p align='center'>
+    <sup>1</sup>Core Contributor&emsp;
+    <sup>2</sup>Corresponding Authors
+</p>
+<div align='center'>
+    <a href='https://antgroup.github.io/ai/echomimic_v3/'><img src='https://img.shields.io/badge/Project-Page-blue'></a>
+    <!-- <a href='https://huggingface.co/BadToBest/EchoMimicV3'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Model-yellow'></a> -->
+    <!--<a href='https://antgroup.github.io/ai/echomimic_v2/'><img src='https://img.shields.io/badge/%F0%9F%A4%97%20HuggingFace-Demo-yellow'></a>-->
+    <!-- <a href='https://modelscope.cn/models/BadToBest/EchoMimicV3'><img src='https://img.shields.io/badge/ModelScope-Model-purple'></a> -->
+    <!--<a href='https://antgroup.github.io/ai/echomimic_v2/'><img src='https://img.shields.io/badge/ModelScope-Demo-purple'></a>-->
+    <a href='https://arxiv.org/abs/2507.03905'><img src='https://img.shields.io/badge/Paper-Arxiv-red'></a>
+    <!-- <a href='https://openaccess.thecvf.com/content/CVPR2025/papers/Meng_EchoMimicV2_Towards_Striking_Simplified_and_Semi-Body_Human_Animation_CVPR_2025_paper.pdf'><img src='https://img.shields.io/badge/Paper-CVPR2025-blue'></a> -->
+    <!-- <a href='https://github.com/antgroup/echomimic_v2/blob/main/assets/halfbody_demo/wechat_group.png'><img src='https://badges.aleen42.com/src/wechat.svg'></a> -->
+</div>
+<!-- <div align='center'>
+    <a href='https://github.com/antgroup/echomimic_v3/discussions/0'><img src='https://img.shields.io/badge/English-Common Problems-orange'></a>
+    <a href='https://github.com/antgroup/echomimic_v3/discussions/1'><img src='https://img.shields.io/badge/中文版-常见问题汇总-orange'></a>
+</div> -->
+
+## &#x1F680; EchoMimic Series
+* EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation. [GitHub](https://github.com/antgroup/echomimic_v3)
+* EchoMimicV2: Towards Striking, Simplified, and Semi-Body Human Animation. [GitHub](https://github.com/antgroup/echomimic_v2)
+* EchoMimicV1: Lifelike Audio-Driven Portrait Animations through Editable Landmark Conditioning. [GitHub](https://github.com/antgroup/echomimic)
+
+
+## &#x1F4E3; Updates
+<!-- * [2025.02.27] 🔥 EchoMimicV2 is accepted by CVPR 2025.
+* [2025.01.16] 🔥 Please check out the [discussions](https://github.com/antgroup/echomimic_v2/discussions) to learn how to start EchoMimicV2.
+* [2025.01.16] 🚀🔥 [GradioUI for Accelerated EchoMimicV2](https://github.com/antgroup/echomimic_v2/blob/main/app_acc.py) is now available.
+* [2025.01.03] 🚀🔥 **One Minute is All You Need to Generate Video**. [Accelerated EchoMimicV2](https://github.com/antgroup/echomimic_v2/blob/main/infer_acc.py) are released. The inference speed can be improved by 9x (from ~7mins/120frames to ~50s/120frames on A100 GPU).
+* [2024.12.16] 🔥 [RefImg-Pose Alignment Demo](https://github.com/antgroup/echomimic_v2/blob/main/demo.ipynb) is now available, which involves aligning reference image, extracting pose from driving video, and generating video.
+* [2024.11.27] 🔥 [Installation tutorial](https://www.youtube.com/watch?v=2ab6U1-nVTQ) is now available. Thanks [AiMotionStudio](https://www.youtube.com/@AiMotionStudio) for the contribution.
+* [2024.11.22] 🔥 [GradioUI](https://github.com/antgroup/echomimic_v2/blob/main/app.py) is now available. Thanks @gluttony-10 for the contribution.
+* [2024.11.22] 🔥 [ComfyUI](https://github.com/smthemex/ComfyUI_EchoMimic) is now available. Thanks @smthemex for the contribution.
+* [2024.11.21] 🔥 We release the EMTD dataset list and processing scripts.
+* [2024.11.21] 🔥 We release our [EchoMimicV2](https://github.com/antgroup/echomimic_v2) codes and models. -->
+<!-- * [2025.08.08] 🔥 We release our [codes](https://arxiv.org/abs/2507.03905). -->
+* [2025.07.08] 🔥 Our [paper](https://arxiv.org/abs/2507.03905) is in public on arxiv.
+
+## &#x1F305; Gallery
+<p align="center">
+  <img src="asset/echomimicv3.jpg"  height=700>
+</p>
+<table class="center">
+<tr>
+    <td width=100% style="border: none">
+        <video controls loop src="https://github.com/user-attachments/assets/f33edb30-66b1-484b-8be0-a5df20a44f3b" muted="false"></video>
+    </td>
+</tr>
+</table>
+For more demo videos, please refer to the project page.
+
+## Quick Start
+### Environment Setup
+- Tested System Environment: Centos 7.2/Ubuntu 22.04, Cuda >= 12.1
+- Tested GPUs: A100(80G) / RTX4090D (24G) / V100(16G)
+- Tested Python Version: 3.10 / 3.11
+
+### 🛠️Installation
+#### 1. Create a conda environment and install pytorch, xformers
+```
+conda create -n echomimic_v3 python=3.10
+conda activate echomimic_v3
+```
+
+#### 2. Other dependencies
+```
+pip install -r requirements.txt
+```
+### 🧱Model Preparation
+
+| Models        |                       Download Link                                           |    Notes                      |
+| --------------|-------------------------------------------------------------------------------|-------------------------------|
+| Wan2.1-Fun-1.3B-InP  |      🤗 [Huggingface](https://huggingface.co/spaces/alibaba-pai/Wan2.1-Fun-1.3B-InP)       | Base model
+| wav2vec2-base |      🤗 [Huggingface](https://huggingface.co/facebook/wav2vec2-base-960h)          | Audio encoder
+| EchoMimicV3      |      🤗 [Huggingface](https://huggingface.co/BadToBest/EchoMimicV3)              | Our weights
+
+-- The **weights** is organized as follows.
+
+```
+./models/
+├── Wan2.1-Fun-1.3B-InP
+├── wav2vec2-base-960h
+└── transformer
+    └── diffusion_pytorch_model.safetensors
+### 🔑 Quick Inference
+```
+python infer.py
+```
+> Tips
+> - Audio CFG: Audio CFG works optimally between 2~3. Increase the audio CFG value for better lip synchronization, while decreasing the audio CFG value can improve the visual quality.
+> - Text CFG: Text CFG works optimally between 4~6. Increase the text CFG value for better prompt following, while decreasing the text CFG value can improve the visual quality.
+> - TeaCache: The optimal range for `--teacache_thresh` is between 0~0.1.
+> - Sampling steps: 5 steps for talking head, 15~25 steps for talking body. 
+> - ​Long video generation: If you want to generate a video longer than 138 frames, you can use Long Video CFG.
+
+
+## 📝 TODO List
+| Status | Milestone                                                                |     
+|:--------:|:-------------------------------------------------------------------------|
+|    2025.08.08    | The inference code of EchoMimicV3 meet everyone on GitHub   | 
+|    🚀    | Preview version Pretrained models trained on English and Chinese on HuggingFace | 
+|    🚀    | Preview version Pretrained models trained on English and Chinese on ModelScope   | 
+|    🚀    | 720P Pretrained models trained on English and Chinese on HuggingFace | 
+|    🚀    | 720P Pretrained models trained on English and Chinese on ModelScope   | 
+|    🚀    | The training code of EchoMimicV3 meet everyone on GitHub   | 
+
+
+
+## &#x1F4D2; Citation
+
+If you find our work useful for your research, please consider citing the paper :
+
+```
+@misc{meng2025echomimicv3,
+  title={EchoMimicV3: 1.3B Parameters are All You Need for Unified Multi-Modal and Multi-Task Human Animation},
+  author={Rang Meng, Yan Wang, Weipeng Wu, Ruobing Zheng, Yuming Li, Chenguang Ma},
+  year={2025},
+  eprint={2507.03905},
+  archivePrefix={arXiv}
+}
+```
+
+## &#x1F31F; Star History
+[![Star History Chart](https://api.star-history.com/svg?repos=antgroup/echomimic_v3&type=Date)](https://star-history.com/#antgroup/echomimic_v3&Date)

echomimicv3-flash-pro/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "WanTransformerAudioMask3DModel",
+  "_diffusers_version": "0.31.0",
+  "add_control_adapter": false,
+  "add_ref_conv": false,
+  "cross_attn_norm": true,
+  "dim": 1536,
+  "eps": 1e-06,
+  "ffn_dim": 8960,
+  "freq_dim": 256,
+  "hidden_size": 1536,
+  "in_channels": 36,
+  "in_dim": 36,
+  "in_dim_control_adapter": 24,
+  "in_dim_ref_conv": 16,
+  "model_type": "i2v",
+  "num_heads": 12,
+  "num_layers": 30,
+  "out_dim": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "qk_norm": true,
+  "text_dim": 4096,
+  "text_len": 512,
+  "window_size": [
+    -1,
+    -1
+  ]
+}

echomimicv3-flash-pro/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ebdbb2fc709108bf2a1728fd92eb2874804e4bc0324e92a2cd55425968c85a4
+size 3727671120

transformer/config.json

@@ -0,0 +1,32 @@
+{
+  "_class_name": "WanTransformerAudioMask3DModel",
+  "_diffusers_version": "0.32.2",
+  "add_control_adapter": false,
+  "add_ref_conv": false,
+  "cross_attn_norm": true,
+  "dim": 1536,
+  "eps": 1e-06,
+  "ffn_dim": 8960,
+  "freq_dim": 256,
+  "hidden_size": 1536,
+  "in_channels": 36,
+  "in_dim": 36,
+  "in_dim_control_adapter": 24,
+  "in_dim_ref_conv": 16,
+  "model_type": "i2v",
+  "num_heads": 12,
+  "num_layers": 30,
+  "out_dim": 16,
+  "patch_size": [
+    1,
+    2,
+    2
+  ],
+  "qk_norm": true,
+  "text_dim": 4096,
+  "text_len": 512,
+  "window_size": [
+    -1,
+    -1
+  ]
+}

transformer/diffusion_pytorch_model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ba25a75c7511ba57a346480d50567b57270282c1f3ab121558c07b65a97adf1f
+size 3414541616