Stable WarpFusion v0.31 - Depth Anything, QoL (Patreon)

Local install guides:
Windows: https://github.com/Sxela/WarpFusion#local-installation-guide-for-windows-venv
Linux: https://github.com/Sxela/WarpFusion/blob/main/README.md#local-installation-guide-for-linux-ubuntu-2204-venv

If something's not working, make a new env and grab a fresh install.bat from that repo first, ask questions later :D

This notebook needs an updated transformers 4.31.0 package. Make a new env with a fresh install.bat or update the package by running !pip install transformers==4.31.0 in a new code cell.

Changelog: 

• only keep 1 output video if keep_audio is on (issue #92 by #orinthesky)

• save alpha.mp4 to batch folder/videoframes (issue #95 by #orinthesky)

• add "do the run" cell behavior switch: render, render+preview maps, only preview maps, skip cell (issue #93 by #orinthesky)

• add alpha, consistency, init image preview to controlnet preview mode

• add schedules for missed_consistency_weight, overshoot_consistency_weight, edges_consistency_weight, consistency_blur, consistency_dilate, soften_consistency_mask (issue #96 by #orinthesky)

• stack previews into a single image and downscale to preview size by default

• add animatediff sdxl mode

• add animatediff sdxl motion module download

• add sdxl controlnets to animatediff sdxl mode

• fix controlnet with preprocessing off not working thanks to #stabilityaiart

• add depth anything annotator from Mikubill/sd-webui-controlnet

• add depth anything annotator ckpt from LiheYoung/Depth-Anything

• add depth anything controlnet from LiheYoung/Depth-Anything \ (issue #99)

• add depth anything controlnet checkpoint from LiheYoung/Depth-Anything

• make depth anything depth estimator work with other depth controlnets (don't color depth maps)

• make other depth estimators work with depth anything controlnet (color depth maps)

• add text label to preview images

18.3.2024:

• move to L tier 

28.7.2024

• move to M tier

Input images, maps, controlnet previews

All used maps will be previewed now if you select render mode that has preview maps in it.
They will now include controlnet detections, init image (the image that is being feed into diffusion model), consistency mask, alpha mask.  
They will be stacked and labeled as well. You can disable stacking and labeling in advanced settings cell in the notebook. 

Render cell modes 

Do the Run! -> render_mode

You can select the render cell behavior: render, render+preview maps, only preview maps, skip cell.
Render just renders the frames, render+preview maps - renders and shows map previews, only preview maps - skips render, previews maps, skip cell - skips render cell, useful when you only need to save the output video. 

Consistency schedules 

GUI -> consistency 

missed_consistency_weight, overshoot_consistency_weight, edges_consistency_weight, consistency_blur, consistency_dilate, soften_consistency_mask are now schedules, so you can dynamically adjust them.

Depth Anything 

GUI -> controlnet -> control_sd15_depth_anything

Check to enable depth anything controlnet in sd1.5 mode. Depth anything controlnet was trained on a depth map with applied heatmap coloring, so it will be automatically colored even if you don't use the depth anything preprocessor and use Zoe or Midas instead. 

GUI -> controlnet -> control_sd15_depth_detector -> depth_anything

Select depth_anything as control_sd15_depth_detector to enable is as the depth preprocessor. Works with other depth controlnets, not only dedpth anything controlnet.

Animatediff SDXL 

define SD + K functions, load model -> model_version -> control_multi_animatediff_sdxl

Doesn't work well (works the same as in comfyui - ok-ish without controlnets, really bad with controlnets)

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!

• 25.08.2023, ComfyWarp v0.1 WarpFusion: Warp and Consistency explanation in ComfyUI

• 2.09.2023, ComfyWarp v0.2 WarpFusion: ComfyWarp iteration 2.

• 3.09.2023, v0.16+ WarpFusion - Multiple Masked Prompts Guide

• 10.10.2023, ComfyWarp v0.4 WarpFusion: ComfyWarp v0.4.2 (schedulers, flow_blend)

• 4.11.2023, ComfyWarp v0.5 WarpFusion: ComfyWarp v0.5 - FixedQueue

• 13.11.2023, v0.27 Stable WarpFusion v0.27 - Changelog

YouTube playlist with settings:
https://www.youtube.com/watch?v=wvvcWm4Snmc&list=PL2cEnissQhlCUgjnGrdvYMwUaDkGemLGq

For tech support and other questions please join our discord server:
https://discord.gg/58Rd73uAe7

Discord is the preferred method because it is nearly impossible to provide any decent help or tech support via Patreon due to its limited text formatting and inability to add screenshots or videos to comments or DMs.
Due to the recent Patreon comments update it's impossible to reply to comments from notifications anymore, so if your comment hasn't been replied to for a while, DM me.