OpenMMLab Multimodal Advanced, Generative, and Intelligent Creation Toolbox. Unlock the magic 🪄: Generative-AI (AIGC), easy-to-use APIs, awsome model zoo, diffusion models, for text-to-image generation, image/video restoration/enhancement, etc.
We are excited to announce the release of MMEditing 1.0.0rc3. This release supports 43+ models, 170+ configs and 169+ checkpoints in MMGeneration and MMEditing. We highlight the following new features
mmdet
and clip
to optional requirements.try_import
for mmdet
. (#1408)try_import
for flip
. (#1420).gitignore
. ($1416)real_feat
to cpu in inception_utils
. (#1415)A total of 5 developers contributed to this release. @Z-Fran, @zengyh1900, @plyfager, @LeoXing1996, @ruoningYu.
We are excited to announce the release of MMEditing 1.0.0rc2. This release supports 43+ models, 170+ configs and 169+ checkpoints in MMGeneration and MMEditing. We highlight the following new features
We want to sincerely thank our community for continuously improving MMEditing. 🥰🥰🥰
forward
. (#1328)preprocess_div2k_dataset.py
. (#1380)PackGenInputs
and GenDataSample
). (#1382)GenerateFacialHeatmap
as np.float32
. (#1310)unpaired_dataset.py
and urls in cyclegan's README. (#1308)A total of 7 developers contributed to this release. Thanks @LeoXing1996, @Z-Fran, @zengyh1900, @plyfager, @ryanxingql, @ruoningYu, @gaoyang07.
Full Changelog: https://github.com/open-mmlab/mmediting/compare/v1.0.0rc1...v1.0.0rc2
VisualizationHook
is deprecated. Users should use MMEditVisualizationHook
instead. (#1375)
Old Version | Current Version |
|
|
---|
preprocess_div2k_dataset.py
. (#1381)mmedit/models/video_interpolators
when importing FLAVR
. (#1186)restoration_video_inference.py
. (#1262)A total of 5 developers contributed to this release. Thanks @LeoXing1996, @Z-Fran, @zengyh1900, @ryanxingql, @ruoningYu.
Full Changelog: https://github.com/open-mmlab/mmediting/compare/v0.15.2...v0.16.0
MMEditing 1.0.0rc0 is the first version of MMEditing 1.x, a part of the OpenMMLab 2.0 projects.
Built upon the new training engine, MMEditing 1.x unifies the interfaces of dataset, models, evaluation, and visualization.
And there are some BC-breaking changes. Please check the migration tutorial for more details.
Bug Fixes
Improvements
Contributors
@wangruohui @Yshuo-Li
Highlights
New Features
use_cache
and backend
in LoadImageFromFileList (#857)after_val_epoch
in IterBaseRunner (#861)Bug Fixes
-
to _
for restoration_demo.py (#834),
in multi-line F-string in crop.py (#855)lq_path
to gt_path
in test_pipeline (#862)Improvements
--cfg-options
in train/test scripts (#826)myst_heading_anchors
(#887)Contributors
@wangruohui @quincylin1 @nijkah @jayagami @ckkelvinchan @ryanxingql @NK-CS-ZZL @Yshuo-Li
Highlights
New Features
--diff-seed
to set different torch seed on different rank (#781)Bug Fixes
flip_ratio
in RandomAffine
pipeline (#799)Improvements
clamp(0, 1)
in test of video frame interpolation (#805)Contributors
@wangruohui @ckkelvinchan @Yshuo-Li @nijkah @wdmwhh @freepoet @quincylin1
Highlights
New Features
Bug Fixes
MMCV
in Dockerfile (#708)__init__
in TestVFIDataset
(#731)Improvements
package.version.parse
(#723)Contributors
@wangruohui @ckkelvinchan @Yshuo-Li @quincylin1 @Juggernaut93 @anse3832 @nijkah