d99afebbdc
new telegram group link
Colombo
2020-06-11 17:39:36 +04:00
82f405ed49
Trainer: fixed "Choose image for the preview history". Now you can switch between subpreviews using 'space' key. Fixed "Write preview history". Now it writes all subpreviews in separated folders https://i.imgur.com/IszifCJ.jpg also the last preview saved as _last.jpg before the first file https://i.imgur.com/Ls1AOK4.jpg thus you can easily check the changes with the first file in photo viewer
Colombo
2020-06-10 10:20:13 +04:00
5c315cab68
XSegEditor: added text label of total labeled images Changed frame line design Changed loading frame design
Colombo
2020-06-09 22:04:15 +04:00
dc43f5a891
add second headswap example
Colombo
2020-06-09 16:01:47 +04:00
c2b5f80e3f
upd readme download link
Colombo
2020-06-08 15:03:40 +04:00
af98407f06
SAEHD: lr_dropout now can be ‘n’, ‘y’, ‘cpu’. ‘n’ and ’y’ are the same as before. ‘cpu’ mean enabled on CPU. This allows not to use extra VRAM, sacrificing 20% time of iteration.
Colombo
2020-06-08 14:18:33 +04:00
f91a604c6d
Manual extractor: now you can specify face rectangle manually using ‘R Mouse button’. It is useful for small, blurry, undetectable faces, animal faces. https://i.imgur.com/8kmVgg8.jpg Warning: such frames must be used only with XSeg workflow ! Landmarks cannot be placed on the face precisely, and they are actually used for positioning the red frame. Try to keep the red frame the same as the adjacent frames.
Colombo
2020-06-02 12:31:24 +04:00
2cc0e64572
Merger: added mask mode ‘learned-prd + learned-dst’ – produces largest area of both dst and predicted masks
Colombo
2020-04-13 22:04:24 +04:00
2b7364005d
Added new face type : head Now you can replace the head. Example: https://www.youtube.com/watch?v=xr5FHd0AdlQ Requirements: Post processing skill in Adobe After Effects or Davinci Resolve. Usage: 1) Find suitable dst footage with the monotonous background behind head 2) Use “extract head” script 3) Gather rich src headset from only one scene (same color and haircut) 4) Mask whole head for src and dst using XSeg editor 5) Train XSeg 6) Apply trained XSeg mask for src and dst headsets 7) Train SAEHD using ‘head’ face_type as regular deepfake model with DF archi. You can use pretrained model for head. Minimum recommended resolution for head is 224. 8) Extract multiple tracks, using Merger: a. Raw-rgb b. XSeg-prd mask c. XSeg-dst mask 9) Using AAE or DavinciResolve, do: a. Hide source head using XSeg-prd mask: content-aware-fill, clone-stamp, background retraction, or other technique b. Overlay new head using XSeg-dst mask
Colombo
2020-04-04 09:28:06 +04:00
6d3607a13d
New script: 5.XSeg) data_dst/src mask for XSeg trainer - fetch.bat Copies faces containing XSeg polygons to aligned_xseg\ dir. Useful only if you want to collect labeled faces and reuse them in other fakes.
Colombo
2020-03-30 14:00:40 +04:00
Colombo
