Changelog
NEXT
Add support for DeepFaceLive models
Add download providers
github
andhuggingface
Introduce
HifiFace
face swapper modelIntroduce
batch-run
command for sequential processingRelease five popular frame enhancer models
Add video encoder
h264_qsv
andhevc_qsv
Update to latest Gradio 5
Refresh the look of the light and dark theme
Gracefully close webcam stream on exit
Polish age modifier processor to reduce halo effect
Introduce
--temp-path
argument to alter temporary resourcesAutomate the deployment to docker hub
Enforce
libvpx-vp9
codec forwebm
processingResolve inconsistent preview updates
Fix incorrect video lengths when replacing audio
Fix OpenVINO issue by aliasing
GPU.0
toGPU
3.0.1
Fix broken
python-multipart
dependency
3.0.0
Revamp the architecture where everything is a job
Introduce
pixel boost
to the face swappersAdd multi angle processing to the face detectors
Introduce age modifier processor
Introduce Live Portrait powered expression restorer processor
Introduce Live Portrait powered face editor processor
Replace face parser with
bisenet_resnet_34
modelRelease the
GHOST
face swapper modelsRelease frame enhancer
real_esrgan_x8
modelsIntroduce ArcFace converter models for SimSwap and GHOST
Introduce offline first assets based on local hash validation
Replace
gender_age
with superiorfairface
modelTransfer
order
,age
andgender
to the face selectorSupport CUDA 12.4, TensorRT 10.4, OpenVINO 2024.1 and ROCm 6.2
Provide appropriate error codes in headless mode
Migrate the CLI to commands along with related arguments
Introduce custom made
peppa_wutz
face landmark modelIntroduce
--face-landmark-model
argumentIntroduce
--output-audio-encoder
argumentAdd video encoder
h264_videotoolbox
andhevc_videotoolbox
Change the
--face-selector-order
default to large-smallReplace globals with a context aware inference manager
Use audio whenever defined via source
Tweak the UI layout and visual appearance
Update to latest Gradio 4
Provide a multi range slider to trim video frames
Introduce a log level aware terminal component to the UI
Ensure significantly more accurate benchmark results
Drop the face detector model
yunet
due low accuracyFix flicker in the face swapper
uniface
modelFix threading and preview crashes for ROCm and DirectML
Fix image quality for
webp
imagesFix the termination of
ffmpeg
processing
2.6.1
Fix broken
numpy
dependency
2.6.0
Introduce a standalone one-click installer for Windows
Add the frame enhancer
clear_reality_x4
andultra_sharp_x4
modelLoad different
ini
files via the--config
argumentIntroduce
--open-browser
to open browser once the program is readyIntroduce
--execution-device-id
to select processing deviceSupport for Intel Arc using the OpenVINO execution provider
Prevent Gradio from converting videos larger than 512 MB in size
Fix path issues on Windows related to special characters
Fix issues when finalizing images using temporary files
2.5.3
Disable Gradio Analytics to prevent version alerts
2.5.2
Introduce dynamic frame colorizer sizes
Validate
facefusion.ini
overrides to prevent crashesRemove GPU architecture lookup to support outdated
nvidia-smi
Remove
hwaccel
which surprisingly improves the FFmpeg performanceFix threading and preview crashes for DirectML
Fix
--output-video-resolution
from not being applied
2.5.1
Add missing
deoldify
models to the frame colorizerFix over-correction by voice extractor on background audio
Fix excessive VRAM consumption of the voice extractor
Fix exception in
conditional_download
while model removalFix stuck processing when using FFmpeg 7
2.5.0
Introduce the frame colorizer using the
ddcolor
anddeoldify
modelExtract voice from the audio to enhance the lip-syncer quality
Experimental 5 to 68 face landmark estimation
Add the face enhancer
gpen_bfr_1024
andgpen_bfr_2048
modelAdd the frame enhancer
real_esrgan_x2
andreal_hatgan_x4
modelIntroduce
--force-download
to download every model at onceMigrate the documentation and installer from venv to conda
Full compatibility with CUDA 12 due
inswapper_128_fp16
model fixFix fps boosting and lowering during video merging
Fix crashes when using
--skip-download
when models are absentFix
h264_nvenc
andhevc_nvenc
presets mapping
2.4.1
Conditional download face analyser models
Prevent download loop when remote is unreachable
Dynamic
concurrency_count
for ideal Gradio performanceMonkey patch Gradio for faster preview and stream rendering
Fix preview for audio to image
2.4.0
Run multiple face detectors simultaneously
Prevent the 68 to 5 face landmark transformation on low confidence
Add the high performance
scrfd
face detector modelGracefully start and stop processing
Introduce ONNX powered frame enhancers
Introduce
--face-landmarker-score
argumentRender tabs when using multiple UI layouts
Introduce
--output-image-resolution
argumentAdd more face debugger items and refine their color theme
Print internal statistics when
--log-level debug
is enabledKeep lips over the whole video once lip syncer is enabled
Restrict resolution upscaling and fps boosting for temporary resources
Add support for
h264_amf
andhevc_amf
video encodersChange the
--output-path
behaviour and normalizationRemove
--temp-frame-quality
argumentFix green line when using a target with uneven pixels
Fix preview of lip syncer when using
--trim-frame-start
Fix the blank output issue for Geforce GTX 16 series
2.3.0
Introduce the lip-syncer processors using
wave2lip
Improve face alignment with 68 to 5 face landmark transformation
Add face swapper model
uniface_256
Add
yoloface
as the default face detector modelClear temporary resources before processing
Add
age
andgender
to the face debugger itemsUpdate installer to version specific CUDA and ROCM entries
Improve the description of the CLI arguments
Enforce
--output-video-resolution
after upscalingReduce terminal output noise while processing
2.2.1
Replace
restoreformer
with the latestrestoreformer_plus_plus
modelFix error when the
facefusion.ini
file is missing a sectionFix image to image when utilizing
--video-memory-strategy tolerant
2.2.0
Significant improve the CUDA performance
Allow default overrides through the
facefusion.ini
fileEnable faster
inswapper_128_fp16
model as defaultAdd
--video-memory-strategy
to trade VRAM usage for speedAdd
bmp
to the--temp-frame-format
argumentAdd compatibility with Pinokio 1.0.0
Display the processing time in the terminal on success
Introduce
--output-video-preset
which defaults toveryfast
Introduce
--output-video-fps
argumentIntroduce
--output-video-resolution
argumentBlock the preview and webcam until models are fully downloaded
Rename
--max-memory
to--system-memory-limit
Fix gender detection due incorrect matrix transformation
Fix render issues when toggling face debugger items repeatedly
2.1.3
Fix installer option for
directml
under Windows
2.1.2
Add CUDA nightly to the installer
Refresh reference faces on processor change
Fix rounding issues of number based CLI arguments
2.1.1
Remove falsy clear reference faces in preview
2.1.0
Add face occlusion masking
Add face region masking with selectable regions
Average source face from multiple images
Multi processing aware reference faces
Only process the reference with face enhancer
Introduce
debug
,info
,warn
anderror
log levelsRestore face alignment offset from retinaface
Enforce virtual environment via installer
Reduce the installer options according to platform
Add
onnxruntime-rocm
support to installerFix preview updates on slider release
Fix preview updates on face reference change
Fix similarity transformation for the face alignment
2.0.0
Add
blendswap_256
,simswap_256
andsimswap_512_unofficial
to the face swapperAdd
gpen_bfr_256
andrestoreformer
to the face enhancerHigh performance face detector using the
retinaface
oryunet
modelsAdd ROCm and OpenVINO support to the frame enhancers
Add support for
webp
images andwebm
videosAdd the
best-worst
andworst-best
to--face-analyser-order
Introduce the
face_debugger
to visualize the bounding box, key points and face maskIntroduce the
facefusion-pinokio
repository to our GitHub organizationIntroduce
--face-mask-blur
and--face-mask-padding
argumentsIntroduce
--face-detector-size
and--face-detector-score
argumentsExtend face selector by
one
modeRemove
insightface
dependency due handcrafted frame processingRemove
tensorflow
andPIL
dependencies duo handcrafted frame analysingSimplify progress bar to reduce performance hits
Improve reference face UI for large amount of people
Webcam mode
udp
andv4l2
now with solid 25fps at 1080pSeamless start and stop the webcam feed
Rename
--face-recognition
to--face-selector-mode
Rename
--face-analyser-direction
to--face-analyser-order
Fix output validation after processing
Apply fixed ranges to number based CLI arguments
Normalize the
--reference-face-distance
calculation to a 0-1 rangeNormalize the
--output-path
even without specified--source-path
Set a 10 seconds timeout for download lookups
1.3.1
Refine
default
andcpu
choices for the installer
1.3.0
Add high performance
fp16
version to the face swapperAdd ONNX powered
CodeFormer
,GFPGAN
andGPEN
to the face enhancerAdd
RealESRGAN_x2plus
andRealESRNet_x4plus
to the frame enhancerImplement blending for the face enhancer and frame enhancer
Enable processors to have options and CLI arguments
Refine the UI theme to a minimal and flat design
Enhance the
--help
and documentation with arguments groupingReduce the default image and video quality to 80 percent
Introduce a new
--torch
argument to the installerImprove Apple Silicon performance using the latest
onnxruntime
Fix video quality to compression normalization
Fix stuck downloads caused by the Windows firewall
1.2.1
Perform VRAM clearance after each processing step
Restrict TensorFlow memory consumption to 512 MB
Verify the model files before frame processing
Introduce
--skip-download
to skip automated downloadsUpgrade to the most recent
onnxruntime
version
1.2.0
Establish realtime webcam performance
Optimize reruns by caching the face analyser results
Optimize image read performance through caching
Resume interrupted asset and model downloads
Allow passing
--onnxruntime
toinstall.py
Introduce official
facefusion-colab
repositoryRemove alignments from each UI components
Introduce checkbox group for the settings
Set webcam resolution and fps in the UI
Disallow empty execution providers in the UI
Fix frame range processing on videos with audio
Fix
CUDA
andROCM
Dockerfile to utilize the GPUFix sorting of temp frame paths
1.1.0
Installer for common and acceleration dependencies
Built-in webcam suite that supports
udp
andv4l2
streamingDedicated
--headless
modeAdd Docker support for ROCM
Allow adjustment of
--output-path
via the UIEnhance output path normalization
Single warm-up before starting the benchmark suite
Ability to select runs for the benchmark suite
Enable benchmarking with partial updates
Implement a fully event-driven UI for super responsiveness
Add a max memory slider to select free RAM
Implement conditional UI based on target media type
Introduce
--output-image-quality
option for image outputFix
crf
range forlibvpx
video encoderFix
detect_fps
to work with different encoding
1.0.0
Dynamic UI based on Gradio
Docker support for CPU and CUDA
Replace
--many-faces
by--face-recognition
that takesreference
andmany
valueTwin support: swap multiple faces by one face reference
Introduce
--execution-queue-count
to adjust processing per threadRename
--execution-threads
to--execution-thread-count
Global options direction, age and gender for face analyser
Blur preview and processing hold when NSFW content has been detected
Flip the quality best to worse from 0-100 to 100-0
Trim video via
trim-frame-start
andtrim-frame-end
Built-in benchmark suite
Intensive codebase refactoring
Last updated