ReShot — copy the shot, not the actors. Video → depth map, OpenPose skeleton or canny lines for Seedance 2.0/2.5 reference video, MiniMax H3 Fun ControlNet and Wan VACE. Apache-2.0. Open-sourced by Maosika 猫斯卡 (www.maosika.com), the AI short-drama production system.
Python ai-short-dramaai-videocannycomfyuicontrolnetdepth-anythingdepth-estimationdwposemaosikaminimaxopenposepose-controlnetpose-estimationseedanceshort-dramavideo-generationvideo-to-videowan
colab: measured time (58 s for the 12 s demo on a T4 at fast)
wangfeng22e9c6df32a6
diff --git a/examples/reshot_colab.ipynb b/examples/reshot_colab.ipynbindex d01c65e..10269c7 100644--- a/examples/reshot_colab.ipynb+++ b/examples/reshot_colab.ipynb@@ -114,7 +114,7 @@"execution_count": null,"outputs": [],"source": [- "#@title Run (a 12 s clip takes ~40 s on a T4 at `fast`, ~2 min at `full`)\n",+ "#@title Run (measured on a free T4: the 12 s demo clip takes about a minute at `fast`; `full` is ~2× that)\n","target = \"seedance\" #@param [\"seedance\", \"h3\", \"wan\", \"none\"]\n","quality = \"fast\" #@param [\"fast\", \"full\"]\n","import json, os, shutil, subprocess, time\n",