Derp Learning

Derp Learning 

использую ИИ не по назначению

272subscribers

65posts

Stable WarpFusion v0.22 - RIFE; SAMTrack and GUI fix

  Local install guide: https://github.com/Sxela/WarpFusion#local-installation-guide-for-windows-venv.
A100 or 24 GB card is highly recommended.
Make a new env and grab a fresh install.bat from that repo.
Changelog:
- add rife
- fix samtrack local install for windows
- fix samtrack incorrect frame indexing if starting not from 1st frame
- fix schedules not loading
- fix ---> 81 os.chdir(f'{root_dir}/Real-ESRGAN') file not found error thanks to Leandro Dreger
- hide "warp_mode","use_patchmatch_inpaiting","warp_num_k","warp_forward","sat_scale" from gui as deprecated
- clean up GUI settings setters/getters
- fix contronet not updating in GUI sometimes
- fix io.capture_output error
- fix platform import, gdown install
- fix rife imports
- upd rife repo, thanks to #stabilityaiart for testing
- fix samtrack not saving video
- make samtrack save separate bg mask
- fix multiple prompt error for sdxl
- fix samtrack site-packages url
- fix samtrack missing groundingdino config
- download dummypkl automatically
- fix venv install real-esrgan model folder not being created
- fix "TypeError: eval() arg 1..." error when loading non-existent settings on the initial run
- add error message for model version mismatch
SAMTrack
Samtrack should now download prebuilt binaries for torch v2/cuda 11.x, if you have a different setup, then you will need to get VS Build Tools: https://stackoverflow.com/questions/64261546/how-to-solve-error-microsoft-visual-c-14-0-or-greater-is-required-when-inst
Then install cuda toolkit for your GPU drivers/os: https://developer.nvidia.com/cuda-downloads?target_os=Windows&target_arch=x86_64
Then it should install itself just fine.
RIFE
Interpolates frames. Results example - in this post's video.
Settings are simple:
exponent:
the power of 2 to which to increase the fps. 1 - x2, 2 - x4, 3 - x8, etc.
video_path:
input video to interpolate. can be a folder with frames, but then you need to specify the fps manually.
nth_frame:
extracts only nth frame before interpolation
fps:
output fps (for image folder input only, fps for video will be based on input video's fps to keep the same video duration after interpolation)
If you have a high-fps output video (like 60ps), you can also try skipping frames to reduce high-frequency flicker. If you have already used the nth frame during your video render, skipping frames here may produce weird results.
Local install guide:
https://github.com/Sxela/WarpFusion/blob/main/README.md
Guides made by users:
05.05.2023, v0.10 Video to AI Animation Tutorial For Beginners: Stable WarpFusion + Controlnet | MDMZ
11.05.2023, v0.11 How to use Stable Warp Fusion
13.05.2023, v0.8 Warp Fusion Local Install Guide (v0.8.6) with Diffusion Demonstration
14.05.2023, v0.12 Warp Fusion Alpha Masking Tutorial | Covers Both Auto-Masking and Custom Masking
23.05.2023, v0.12 STABLE WARPFUSION TUTORIAL - Colab Pro & Local Install
15.06.2023, v0.13 AI Animation out of Your Video: Stable Warpfusion Guide (Google Colab & Local Intallation)
17.06.2023, v0.14 Stable Warpfusion Tutorial: Turn Your Video to an AI Animation
21.06.2023, v0.14 Avoiding Common Problems with Stable Warpfusion
21.06.2023, v0.15 Warp Fusion: Step by Step Tutorial
04.07.2023, v0.15 Intense AI Video Maker (Stable WarpFusion Tutorial)
15.08.2023, v0.17 BEST Laptop for AI ( SDXL & Stable Warpfusion ) ft. RTX 4090 - Make AI Art FREE and FAST!
YouTube playlist with settings:
https://www.youtube.com/watch?v=wvvcWm4Snmc&list=PL2cEnissQhlCUgjnGrdvYMwUaDkGemLGq
ipynb
stable_warpfusion_v0_22_23.ipynb750.40 Kb
Go up