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
docs: fix modelscope download syntax in the model card
wangfeng9ae7d108b7ca
diff --git a/docs/MODELSCOPE.md b/docs/MODELSCOPE.mdindex 768a686..0a42784 100644--- a/docs/MODELSCOPE.md+++ b/docs/MODELSCOPE.md@@ -85,7 +85,7 @@ pip install "reshot[pose]" # 需要 PATH 里有 ffmpeg;没有就装 "re```bashpip install modelscope-modelscope download --model maosika/reshot weights/video_depth_anything_vits.pth weights/yolox_l.onnx weights/dw-ll_ucoco_384.onnx --local_dir ./reshot-weights+modelscope download maosika/reshot weights/video_depth_anything_vits.pth weights/yolox_l.onnx weights/dw-ll_ucoco_384.onnx --local-dir ./reshot-weightsreshot 参考片.mp4 -o 深度图.mp4 --checkpoint ./reshot-weights/weights/video_depth_anything_vits.pthreshot 参考片.mp4 -o 骨架.mp4 --control pose --checkpoint-dir ./reshot-weights/weights```