From 2073011473dc25060040ed1497736a3b0dcee453 Mon Sep 17 00:00:00 2001 From: rangoliu Date: Thu, 24 Aug 2023 21:39:30 +0800 Subject: [PATCH] [Release] Release v1.0.2 (#1998) * fix coco dataset for 2017 * changelog * fix sd --- README.md | 12 ++--- README_zh-CN.md | 12 ++--- docs/en/changelog.md | 103 ++++++++++++++++++++++++++++++++++++++++ docs/zh_cn/changelog.md | 102 +++++++++++++++++++++++++++++++++++++++ mmagic/version.py | 2 +- 5 files changed, 218 insertions(+), 13 deletions(-) diff --git a/README.md b/README.md index 1f1dc34b6e..cc87ef0f2c 100644 --- a/README.md +++ b/README.md @@ -57,13 +57,13 @@ English | [简体中文](README_zh-CN.md) ## 🚀 What's New -### New release [**MMagic v1.0.1**](https://github.com/open-mmlab/mmagic/releases/tag/v1.0.1) \[26/05/2023\]: +### New release [**MMagic v1.0.2**](https://github.com/open-mmlab/mmagic/releases/tag/v1.0.2) \[24/08/2023\]: -- Support tomesd for StableDiffusion speed-up. -- Support all inpainting/matting/image restoration models inferencer. -- Support animated drawings. -- Support Style-Based Global Appearance Flow for Virtual Try-On. -- Fix inferencer in pip-install. +- 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/) 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). diff --git a/README_zh-CN.md b/README_zh-CN.md index 40136c7da1..6f93275e14 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -57,13 +57,13 @@ ## 🚀 最新进展 -### 最新的 [**MMagic v1.0.1**](https://github.com/open-mmlab/mmagic/releases/tag/v1.0.1) 版本已经在 \[26/05/2023\] 发布: +### 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: -- 支持 StableDiffusion tomesd 加速. -- 支持所有 inpainting/matting/image restoration 模型的 inferencer. -- 支持 animated drawings. -- 支持 Style-Based Global Appearance Flow for Virtual Try-On. -- 修复 pip install 时 inferencer 无法使用的问题. +- 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/) 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)。 diff --git a/docs/en/changelog.md b/docs/en/changelog.md index f832efa991..9fe1f54e2f 100644 --- a/docs/en/changelog.md +++ b/docs/en/changelog.md @@ -1,5 +1,108 @@ # Changelog +## v1.0.2 (24/08/2023) + +**Highlights** + +**1. More detailed documentation** + +Thank you to the community contributors for helping us improve the documentation. We have improved many documents, including both Chinese and English versions. Please refer to the [documentation](https://mmagic.readthedocs.io/en/latest/) for more details. + +**2. New algorithms** + +- 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) + +From right to left: origin image, DDIM inversion, Null-text inversion + +
+ +
+ +Prompt-to-prompt Editing + +
+ cat -> dog +
+ +
+ +
+ spider man -> iron man(attention replace) +
+ +
+ +
+ Effel tower -> Effel tower at night (attention refine) +
+ +
+ +
+ blossom sakura tree -> blossom(-3) sakura tree (attention reweight) +
+ +
+ +- 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) + +**New Features & Improvements** + +- \[Enhancement\] Support noise offset in stable diffusion training by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1880 +- \[Community\] Support Glide Upsampler by @Taited in https://github.com/open-mmlab/mmagic/pull/1663 +- \[Enhance\] support controlnet inferencer by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1891 +- \[Feature\] support Albumentations augmentation transformations and pipeline by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1894 +- \[Feature\] Add Attention Injection for unet by @liuwenran in https://github.com/open-mmlab/mmagic/pull/1895 +- \[Enhance\] update benchmark scripts by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1907 +- \[Enhancement\] update mmagic docs by @crazysteeaam in https://github.com/open-mmlab/mmagic/pull/1920 +- \[Enhancement\] Support Prompt-to-prompt, ddim inversion and null-text inversion by @FerryHuang in https://github.com/open-mmlab/mmagic/pull/1908 +- \[CodeCamp2023-302\] Support MMagic visualization and write a user guide by @aptsunny in https://github.com/open-mmlab/mmagic/pull/1939 +- \[Feature\] Support Textual Inversion by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1822 +- \[Feature\] Support stable diffusion inpaint by @Taited in https://github.com/open-mmlab/mmagic/pull/1976 +- \[Enhancement\] Adopt `BaseModule` for some models by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1543 +- \[MMSIG\]支持 DeblurGANv2 inference by @xiaomile in https://github.com/open-mmlab/mmagic/pull/1955 +- \[CodeCamp2023-647\] Add new configs of EG3D by @RangeKing in https://github.com/open-mmlab/mmagic/pull/1985 + +**Bug Fixes** + +- Fix dtype error in StableDiffusion and DreamBooth training by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1879 +- Fix gui VideoSlider bug by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1885 +- Fix init_model and glide demo by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1888 +- Fix InstColorization bug when dim=3 by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1901 +- Fix sd and controlnet fp16 bugs by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1914 +- Fix num_images_per_prompt in controlnet by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1936 +- Revise metafile for sd-inpainting to fix inferencer init by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1995 + +**New Contributors** + +- @wyyang23 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1886 +- @yehuixie made their first contribution in https://github.com/open-mmlab/mmagic/pull/1912 +- @crazysteeaam made their first contribution in https://github.com/open-mmlab/mmagic/pull/1920 +- @BUPT-NingXinyu made their first contribution in https://github.com/open-mmlab/mmagic/pull/1921 +- @zhjunqin made their first contribution in https://github.com/open-mmlab/mmagic/pull/1918 +- @xuesheng1031 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1923 +- @wslgqq277g made their first contribution in https://github.com/open-mmlab/mmagic/pull/1934 +- @LYMDLUT made their first contribution in https://github.com/open-mmlab/mmagic/pull/1933 +- @RangeKing made their first contribution in https://github.com/open-mmlab/mmagic/pull/1930 +- @xin-li-67 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1932 +- @chg0901 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1931 +- @aptsunny made their first contribution in https://github.com/open-mmlab/mmagic/pull/1939 +- @YanxingLiu made their first contribution in https://github.com/open-mmlab/mmagic/pull/1943 +- @tackhwa made their first contribution in https://github.com/open-mmlab/mmagic/pull/1937 +- @Geo-Chou made their first contribution in https://github.com/open-mmlab/mmagic/pull/1940 +- @qsun1 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1956 +- @ththth888 made their first contribution in https://github.com/open-mmlab/mmagic/pull/1961 +- @sijiua made their first contribution in https://github.com/open-mmlab/mmagic/pull/1967 +- @MING-ZCH made their first contribution in https://github.com/open-mmlab/mmagic/pull/1982 +- @AllYoung made their first contribution in https://github.com/open-mmlab/mmagic/pull/1996 + ## v1.0.1 (26/05/2023) **New Features & Improvements** diff --git a/docs/zh_cn/changelog.md b/docs/zh_cn/changelog.md index b540f787b2..bf1f234202 100644 --- a/docs/zh_cn/changelog.md +++ b/docs/zh_cn/changelog.md @@ -1,5 +1,107 @@ # 变更日志 +## v1.0.2 (24/08/2023) + +**亮点** + +**1. 更详尽的文档** + +感谢社区的贡献者们帮助我们改进文档。我们已经改进了许多文档，包括中文和英文版本。更多详细信息请参考[文档](https://mmagic.readthedocs.io/zh_CN/latest/)。 + +**2. 新的算法** + +- 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) + +从左到右: origin image, DDIM inversion, Null-text inversion + +
+ +
+ +Prompt-to-prompt 编辑 + +
+ cat -> dog +
+ +
+ +
+ spider man -> iron man(attention replace) +
+ +
+ +
+ Effel tower -> Effel tower at night (attention refine) +
+ +
+ +
+ blossom sakura tree -> blossom(-3) sakura tree (attention reweight) +
+ +
+ +- 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) + +**新功能和改进** + +- \[增强\] 支持在稳定扩散训练中的噪声偏移，由 @LeoXing1996 提交于 https://github.com/open-mmlab/mmagic/pull/1880 ↗ +- \[社区\] 支持 Glide Upsampler，由 @Taited 提交于 https://github.com/open-mmlab/mmagic/pull/1663 ↗ +- \[增强\] 支持 controlnet 推理器，由 @Z-Fran 提交于 https://github.com/open-mmlab/mmagic/pull/1891 ↗ +- \[功能\] 支持 Albumentations 增强变换和流水线，由 @Z-Fran 提交于 https://github.com/open-mmlab/mmagic/pull/1894 ↗ +- \[功能\] 为 unet 添加注意力注入，由 @liuwenran 提交于 https://github.com/open-mmlab/mmagic/pull/1895 ↗ +- \[增强\] 更新基准测试脚本，由 @Z-Fran 提交于 https://github.com/open-mmlab/mmagic/pull/1907 ↗ +- \[增强\] 更新 mmagic 文档，由 @crazysteeaam 提交于 https://github.com/open-mmlab/mmagic/pull/1920 ↗ +- \[增强\] 支持 Prompt-to-prompt、ddim inversion 和 null-text inversion，由 @FerryHuang 提交于 https://github.com/open-mmlab/mmagic/pull/1908 ↗ +- \[CodeCamp2023-302\] 支持 MMagic 可视化并编写用户指南，由 @aptsunny 提交于 https://github.com/open-mmlab/mmagic/pull/1939 ↗ +- \[功能\] 支持textual inversion，由 @LeoXing1996 提交于 https://github.com/open-mmlab/mmagic/pull/1822 ↗ +- \[增强\] 对一些模型采用 BaseModule，由 @LeoXing1996 提交于 https://github.com/open-mmlab/mmagic/pull/1543 ↗ +- \[MMSIG\] 支持 DeblurGANv2 推理，由 @xiaomile 提交于 https://github.com/open-mmlab/mmagic/pull/1955 ↗ +- \[CodeCamp2023-647\] 添加 EG3D 的新配置，由 @RangeKing 提交于 https://github.com/open-mmlab/mmagic/pull/1985 ↗ + +**Bug 修复** + +- 修复了 StableDiffusion 和 DreamBooth 训练中的 dtype 错误。 by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1879 +- 修复了 gui VideoSlider 的 bug。 by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1885 +- 修复了 init_model 和 glide demo 的问题。 by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1888 +- 修复了当 dim=3 时的 InstColorization bug。 by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1901 +- 修复了 sd 和 controlnet 的 fp16 bug。 by @Z-Fran in https://github.com/open-mmlab/mmagic/pull/1914 +- 修复了 controlnet 中的 num_images_per_prompt。 by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1936 +- 修正了 sd-inpainting 的 metafile 以修复推理器的初始化。 by @LeoXing1996 in https://github.com/open-mmlab/mmagic/pull/1995 + +**新贡献者** + +- @wyyang23 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1886 +- @yehuixie 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1912 +- @crazysteeaam 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1920 +- @BUPT-NingXinyu 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1921 +- @zhjunqin 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1918 +- @xuesheng1031 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1923 +- @wslgqq277g 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1934 +- @LYMDLUT 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1933 +- @RangeKing 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1930 +- @xin-li-67 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1932 +- @chg0901 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1931 +- @aptsunny 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1939 +- @YanxingLiu 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1943 +- @tackhwa 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1937 +- @Geo-Chou 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1940 +- @qsun1 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1956 +- @ththth888 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1961 +- @sijiua 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1967 +- @MING-ZCH 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1982 +- @AllYoung 首次贡献于 https://github.com/open-mmlab/mmagic/pull/1996 + ## v1.0.1 (26/05/2023) **新功能和改进** diff --git a/mmagic/version.py b/mmagic/version.py index 5afe64b1a4..75a530f554 100644 --- a/mmagic/version.py +++ b/mmagic/version.py @@ -1,6 +1,6 @@ # Copyright (c) Open-MMLab. All rights reserved. -__version__ = '1.0.2dev0' +__version__ = '1.0.2' def parse_version_info(version_str):