Merge branch 'main' into feat/sdxl_train

README.md

@@ -58,13 +58,13 @@ English | [简体中文](README_zh-CN.md)
 
 ## 🚀 What's New <a><img width="35" height="20" src="https://user-images.githubusercontent.com/12782558/212848161-5e783dd6-11e8-4fe0-bbba-39ffb77730be.png"></a>
 
-### New release [**MMagic v1.0.2**](https://github.com/open-mmlab/mmagic/releases/tag/v1.0.2) \[24/08/2023\]:
+### New release [**MMagic v1.1.0**](https://github.com/open-mmlab/mmagic/releases/tag/v1.1.0) \[22/09/2023\]:
 
-- Support Prompt-to-prompt, DDIM Inversion and Null-text Inversion. [Click to View.](https://github.com/open-mmlab/mmagic/blob/main/projects/prompt_to_prompt/README.md)
-- Support Textual Inversion. [Click to view.](https://github.com/open-mmlab/mmagic/blob/main/configs/textual_inversion/README.md)
-- Support Attention Injection for more stable video generation with controlnet. [Click to view.](https://github.com/open-mmlab/mmagic/blob/main/configs/controlnet_animation/README.md)
-- Support Stable Diffusion Inpainting. [Click to view.](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion/README.md)
-- More detailed documentation. [Click to view.](https://mmagic.readthedocs.io/en/latest/)
+- Support ViCo, a new SD personalization method. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/vico/README.md)
+- Support AnimateDiff, a popular text2animation method. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/animatediff/README.md)
+- Support SDXL（Stable Diffusion XL）. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion_xl/README.md)
+- Support DragGAN implementation with MMagic. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/draggan/README.md)
+- Support FastComposer, a new multi-subject text-to-image generation method. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/fastcomposer/README.md)
 
 We are excited to announce the release of MMagic v1.0.0 that inherits from [MMEditing](https://github.com/open-mmlab/mmediting) and [MMGeneration](https://github.com/open-mmlab/mmgeneration).
 
@@ -162,9 +162,11 @@ The best practice on our main branch works with **Python 3.8+** and **PyTorch 1.
 
 More and more community contributors are joining us to make our repo better. Some recent projects are contributed by the community including:
 
-- [GLIDE](projects/glide/configs/README.md) is contributed by @Taited.
-- [Restormer](configs/restormer/README.md) is contributed by @AlexZou14.
-- [SwinIR](configs/swinir/README.md) is contributed by @Zdafeng.
+- [SDXL](configs/stable_diffusion_xl/README.md) is contributed by  @okotaku.
+- [AnimateDiff](configs/animatediff/README.md) is contributed by @ElliotQi.
+- [ViCo](configs/vico/README.md) is contributed by @FerryHuang.
+- [DragGan](configs/draggan/README.md) is contributed by @qsun1.
+- [FastComposer](configs/fastcomposer/README.md) is contributed by @xiaomile.
 
 [Projects](projects/README.md) is opened to make it easier for everyone to add projects to MMagic.
 
@@ -185,9 +187,9 @@ Install MMCV, MMEngine and MMagic with [MIM](https://github.com/open-mmlab/mim).
 
 ```shell
 pip3 install openmim
-mim install 'mmcv>=2.0.0'
-mim install 'mmengine'
-mim install 'mmagic'
+mim install mmcv>=2.0.0
+mim install mmengine
+mim install mmagic
 ```
 
 **Step 3.**
@@ -267,6 +269,7 @@ Please refer to [installation](docs/en/get_started/install.md) for more detailed
           <li><a href="configs/styleganv1/README.md">StyleGANV1 (CVPR'2019)</a></li>
           <li><a href="configs/styleganv2/README.md">StyleGANV2 (CVPR'2019)</a></li>
           <li><a href="configs/styleganv3/README.md">StyleGANV3 (NeurIPS'2021)</a></li>
+          <li><a href="configs/draggan/README.md">DragGan (2023)</a></li>
         </ul>
       </td>
       <td>
@@ -352,7 +355,7 @@ Please refer to [installation](docs/en/get_started/install.md) for more detailed
         <b>Matting</b>
       </td>
       <td>
-        <b>Text-to-Image</b>
+        <b>Text-to-Image(Video)</b>
       </td>
       <td>
         <b>3D-aware Generation</b>
@@ -388,6 +391,10 @@ Please refer to [installation](docs/en/get_started/install.md) for more detailed
           <li><a href="projects/prompt_to_prompt/README.md">Null-text Inversion (2022)</a></li>
           <li><a href="configs/controlnet/README.md">ControlNet (2023)</a></li>
           <li><a href="configs/controlnet_animation/README.md">ControlNet Animation (2023)</a></li>
+          <li><a href="configs/stable_diffusion_xl/README.md">Stable Diffusion XL (2023)</a></li>
+          <li><a href="configs/animatediff/README.md">AnimateDiff (2023)</a></li>
+          <li><a href="configs/vico/README.md">ViCo (2023)</a></li>
+          <li><a href="configs/fastcomposer/README.md">FastComposer (2023)</a></li>
         </ul>
       </td>
       <td>

README_zh-CN.md

@@ -58,13 +58,13 @@
 
 ## 🚀 最新进展 <a><img width="35" height="20" src="https://user-images.githubusercontent.com/12782558/212848161-5e783dd6-11e8-4fe0-bbba-39ffb77730be.png"></a>
 
-### 最新的 [**MMagic v1.0.2**](https://github.com/open-mmlab/mmagic/releases/tag/v1.0.2) 版本已经在 \[24/08/2023\] 发布:
+### 最新的 [**MMagic v1.1.0**](https://github.com/open-mmlab/mmagic/releases/tag/v1.1.0) 版本已经在 \[22/09/2023\] 发布:
 
-- 支持了 Prompt-to-prompt, DDIM Inversion 和 Null-text Inversion. [点击查看.](https://github.com/open-mmlab/mmagic/blob/main/projects/prompt_to_prompt/README.md)
-- 支持了 Textual Inversion. [点击查看.](https://github.com/open-mmlab/mmagic/blob/main/configs/textual_inversion/README.md)
-- 支持了 Attention Injection 以便使用 controlnet 生成更稳定的视频. [点击查看.](https://github.com/open-mmlab/mmagic/blob/main/configs/controlnet_animation/README.md)
-- 支持了 Stable Diffusion Inpainting. [点击查看.](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion/README.md)
-- 更详尽的文档. [点击查看.](https://mmagic.readthedocs.io/zh_CN/latest/)
+- 支持ViCo，一种新的个性化方法，用于SD（Style Disentanglement）。[点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/vico/README.md)
+- 支持AnimateDiff，一种流行的文本转动画方法。[点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/animatediff/README.md)
+- 支持SDXL（Stable Diffusion XL）方法。[点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion_xl/README.md)
+- 支持DragGAN方法的实现，使用MMagic。[点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/draggan/README.md)
+- 支持FastComposer, 一种新的多主体文本生成图像方法。[点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/fastcomposer/README.md)
 
 我们正式发布 MMagic v1.0.0 版本，源自 [MMEditing](https://github.com/open-mmlab/mmediting) 和 [MMGeneration](https://github.com/open-mmlab/mmgeneration)。
 
@@ -160,9 +160,11 @@ https://user-images.githubusercontent.com/49083766/233564593-7d3d48ed-e843-4432-
 
 越来越多社区贡献者的加入使我们的算法库日益发展。最近由社区贡献的项目包括：
 
-- [GLIDE](projects/glide/configs/README.md) 来自 @Taited.
-- [Restormer](configs/restormer/README.md) 来自 @AlexZou14.
-- [SwinIR](configs/swinir/README.md) 来自 @Zdafeng.
+- [SDXL](configs/stable_diffusion_xl/README.md) 来自 @okotaku.
+- [AnimateDiff](configs/animatediff/README.md) 来自 @ElliotQi.
+- [ViCo](configs/vico/README.md) 来自 @FerryHuang.
+- [DragGan](configs/draggan/README.md) 来自 @qsun1.
+- [FastComposer](configs/fastcomposer/README.md) 来自 @xiaomile.
 
 为使向 MMagic 中添加项目更加容易，我们开启了 [Projects](projects/README.md) 。
 
@@ -264,6 +266,7 @@ pip3 install -e .
           <li><a href="configs/styleganv1/README.md">StyleGANV1 (CVPR'2019)</a></li>
           <li><a href="configs/styleganv2/README.md">StyleGANV2 (CVPR'2019)</a></li>
           <li><a href="configs/styleganv3/README.md">StyleGANV3 (NeurIPS'2021)</a></li>
+          <li><a href="configs/draggan/README.md">DragGan (2023)</a></li>
         </ul>
       </td>
       <td>
@@ -349,7 +352,7 @@ pip3 install -e .
         <b>Matting</b>
       </td>
       <td>
-        <b>Text-to-Image</b>
+        <b>Text-to-Image(Video)</b>
       </td>
       <td>
         <b>3D-aware Generation</b>
@@ -384,7 +387,10 @@ pip3 install -e .
           <li><a href="projects/prompt_to_prompt/README.md">Prompt-to-Prompt (2022)</a></li>
           <li><a href="projects/prompt_to_prompt/README.md">Null-text Inversion (2022)</a></li>
           <li><a href="configs/controlnet/README.md">ControlNet (2023)</a></li>
-          <li><a href="configs/controlnet_animation/README.md">ControlNet Animation (2023)</a></li>
+          <li><a href="configs/stable_diffusion_xl/README.md">Stable Diffusion XL (2023)</a></li>
+          <li><a href="configs/animatediff/README.md">AnimateDiff (2023)</a></li>
+          <li><a href="configs/vico/README.md">ViCo (2023)</a></li>
+          <li><a href="configs/fastcomposer/README.md">FastComposer (2023)</a></li>
         </ul>
       </td>
       <td>

docs/en/changelog.md

@@ -1,5 +1,85 @@
 # Changelog
 
+## v1.1.0 (22/09/2023)
+
+**Highlights**
+
+In this new version of MMagic, we have added support for the following five new algorithms.
+
+- Support ViCo, a new SD personalization method. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/vico/README.md)
+
+<table align="center">
+<thead>
+  <tr>
+    <td>
+<div align="center">
+  <img src="https://github.com/open-mmlab/mmagic/assets/71176040/58a6953c-053a-40ea-8826-eee428c992b5" width="800"/>
+  <br/>
+</thead>
+</table>
+
+- Support AnimateDiff, a popular text2animation method. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/animatediff/README.md)
+
+![512](https://github.com/ElliotQi/mmagic/assets/46469021/54d92aca-dfa9-4eeb-ba38-3f6c981e5399)
+
+- Support SDXL. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion_xl/README.md)
+
+<div align=center>
+<img src="https://github.com/okotaku/diffengine/assets/24734142/27d4ebad-5705-4500-826f-41f425a08c0d"/>
+</div>
+
+- Support DragGAN implementation with MMagic. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/draggan/README.md)
+
+<div align=center>
+<img src="https://github.com/open-mmlab/mmagic/assets/55343765/7c397bd0-fa07-48fe-8a7c-a4022907404b"/>
+</div>
+
+- Support for FastComposer. [Click to View](https://github.com/open-mmlab/mmagic/blob/main/configs/fastcomposer/README.md)
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/14927720/265914135-8a25789c-8d30-40cb-8ac5-e3bd3b617aac.png">
+</div>
+
+**New Features & Improvements**
+
+- \[Feature\] Support inference with diffusers pipeline, sd_xl first. by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2023
+- \[Enhance\] add negative prompt for sd inferencer by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2021
+- \[Enhance\] Update flake8 checking config in setup.cfg by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/2007
+- \[Enhance\] Add ‘config_name' as a supplement to the 'model_setting' by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2027
+- \[Enhance\] faster test by @okotaku in https://github.com/open-mmlab/mmagic/pull/2034
+- \[Enhance\] Add OpenXLab Badge by @ZhaoQiiii in https://github.com/open-mmlab/mmagic/pull/2037
+
+**CodeCamp Contributions**
+
+- \[CodeCamp2023-643\] Add new configs of BigGAN by @limafang in https://github.com/open-mmlab/mmagic/pull/2003
+- \[CodeCamp2023-648\] MMagic new config GuidedDiffusion by @ooooo-create in https://github.com/open-mmlab/mmagic/pull/2005
+- \[CodeCamp2023-649\] MMagic new config Instance Colorization by @ooooo-create in https://github.com/open-mmlab/mmagic/pull/2010
+- \[CodeCamp2023-652\] MMagic new config StyleGAN3 by @hhy150 in https://github.com/open-mmlab/mmagic/pull/2018
+- \[CodeCamp2023-653\] Add new configs of Real BasicVSR by @RangeKing in https://github.com/open-mmlab/mmagic/pull/2030
+
+**Bug Fixes**
+
+- \[Fix\] Fix best practice and back to contents on mainpage, add new models to model zoo by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2001
+- \[Fix\] Check CI error and remove main stream gpu test by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2013
+- \[Fix\] Check circle ci memory by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2016
+- \[Fix\] remove code and fix clip loss ut test by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2017
+- \[Fix\] mock infer in diffusers pipeline inferencer ut. by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2026
+- \[Fix\] Fix bug caused by merging draggan by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2029
+- \[Fix\] Update QRcode by @crazysteeaam in https://github.com/open-mmlab/mmagic/pull/2009
+- \[Fix\] Replace the download links in README with OpenXLab version by @FerryHuang in https://github.com/open-mmlab/mmagic/pull/2038
+- \[Fix\] Increase docstring coverage by @liuwenran in https://github.com/open-mmlab/mmagic/pull/2039
+
+**New Contributors**
+
+- @limafang made their first contribution in https://github.com/open-mmlab/mmagic/pull/2003
+- @ooooo-create made their first contribution in https://github.com/open-mmlab/mmagic/pull/2005
+- @hhy150 made their first contribution in https://github.com/open-mmlab/mmagic/pull/2018
+- @ZhaoQiiii made their first contribution in https://github.com/open-mmlab/mmagic/pull/2037
+- @ElliotQi made their first contribution in https://github.com/open-mmlab/mmagic/pull/1980
+- @Beaconsyh08 made their first contribution in https://github.com/open-mmlab/mmagic/pull/2012
+
+**Full Changelog**: https://github.com/open-mmlab/mmagic/compare/v1.0.2...v1.0.3
+
 ## v1.0.2 (24/08/2023)
 
 **Highlights**

docs/zh_cn/changelog.md

@@ -1,5 +1,85 @@
 # 变更日志
 
+## v1.1.0 (22/09/2023)
+
+**亮点**
+
+在这次的发版中，我们新支持了下面五个新的算法.
+
+- 支持了 ViCo, 一种新的 SD personalization 算法. [点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/vico/README.md)
+
+<table align="center">
+<thead>
+  <tr>
+    <td>
+<div align="center">
+  <img src="https://github.com/open-mmlab/mmagic/assets/71176040/58a6953c-053a-40ea-8826-eee428c992b5" width="800"/>
+  <br/>
+</thead>
+</table>
+
+- 支持了 AnimateDiff, 一个很火的 text2animation 算法. [点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/animatediff/README.md)
+
+![512](https://github.com/ElliotQi/mmagic/assets/46469021/54d92aca-dfa9-4eeb-ba38-3f6c981e5399)
+
+- 支持了 SDXL. [点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/stable_diffusion_xl/README.md)
+
+<div align=center>
+<img src="https://github.com/okotaku/diffengine/assets/24734142/27d4ebad-5705-4500-826f-41f425a08c0d"/>
+</div>
+
+- 支持了 DragGAN. [点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/draggan/README.md)
+
+<div align=center>
+<img src="https://github.com/open-mmlab/mmagic/assets/55343765/7c397bd0-fa07-48fe-8a7c-a4022907404b"/>
+</div>
+
+- 支持了 FastComposer. [点击查看](https://github.com/open-mmlab/mmagic/blob/main/configs/fastcomposer/README.md)
+
+<div align=center>
+<img src="https://user-images.githubusercontent.com/14927720/265914135-8a25789c-8d30-40cb-8ac5-e3bd3b617aac.png">
+</div>
+
+**新功能和改进**
+
+- \[功能\] 支持使用diffusers pipeline进行推断，首先使用sd_xl。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2023
+- \[增强\] 为sd推理器添加负面提示。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2021
+- \[增强\] 更新setup.cfg中的flake8检查配置。由@LeoXing1996完成，在https://github.com/open-mmlab/mmagic/pull/2007
+- \[增强\] 将'config_name'作为'model_setting'的补充添加。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2027
+- \[增强\] 更快的测试。由@okotaku完成，在https://github.com/open-mmlab/mmagic/pull/2034
+- \[增强\] 添加OpenXLab徽章。由@ZhaoQiiii完成，在https://github.com/open-mmlab/mmagic/pull/2037
+
+**CodeCamp贡献**
+
+- \[CodeCamp2023-643\] 添加BigGAN的新配置。由@limafang完成，在https://github.com/open-mmlab/mmagic/pull/2003
+- \[CodeCamp2023-648\] MMagic的新配置GuidedDiffusion。由@ooooo-create完成，在https://github.com/open-mmlab/mmagic/pull/2005
+- \[CodeCamp2023-649\] MMagic的新配置Instance Colorization。由@ooooo-create完成，在https://github.com/open-mmlab/mmagic/pull/2010
+- \[CodeCamp2023-652\] MMagic的新配置StyleGAN3。由@hhy150完成，在https://github.com/open-mmlab/mmagic/pull/2018
+- \[CodeCamp2023-653\] 添加Real BasicVSR的新配置。由@RangeKing完成，在https://github.com/open-mmlab/mmagic/pull/2030
+
+**Bug 修复**
+
+- \[修复\] 修复主页上的最佳实践和返回目录，将新模型添加到模型库中。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2001
+- \[修复\] 检查CI错误并移除主流GPU测试。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2013
+- \[修复\] 检查Circle CI内存。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2016
+- \[修复\] 移除代码并修复剪辑损失的单元测试。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2017
+- \[修复\] 在diffusers pipeline推理器单元测试中模拟推理。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2026
+- \[修复\] 由于合并draggan而修复的错误。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2029
+- \[修复\] 更新QR码。由@crazysteeaam完成，在https://github.com/open-mmlab/mmagic/pull/2009
+- \[修复\] 用OpenXLab版本替换README中的下载链接。由@FerryHuang完成，在https://github.com/open-mmlab/mmagic/pull/2038
+- \[修复\] 增加文档字符串覆盖率。由@liuwenran完成，在https://github.com/open-mmlab/mmagic/pull/2039
+
+**新贡献者**
+
+- @limafang 首次贡献于 https://github.com/open-mmlab/mmagic/pull/2003
+- @ooooo-create 首次贡献于 https://github.com/open-mmlab/mmagic/pull/2005
+- @hhy150 首次贡献于 https://github.com/open-mmlab/mmagic/pull/2018
+- @ZhaoQiiii 首次贡献于 https://github.com/open-mmlab/mmagic/pull/2037
+- @ElliotQi 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1980
+- @Beaconsyh08 首次贡献于 https://github.com/open-mmlab/mmagic/pull/2012
+
+**完整更新日志**: https://github.com/open-mmlab/mmagic/compare/v1.0.2...v1.0.3
+
 ## v1.0.2 (24/08/2023)
 
 **亮点**

mmagic/version.py

@@ -1,6 +1,6 @@
 # Copyright (c) Open-MMLab. All rights reserved.
 
-__version__ = '1.0.3dev0'
+__version__ = '1.1.0dev0'
 
 
 def parse_version_info(version_str):