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
Changelog
0.5.0 — 2026-09-14
- Skeleton output —
--control pose(closes #6). DWPose (YOLOX-L person detector + RTMPose whole-body estimator, Apache-2.0 code and weights) in ONNX Runtime, drawn in the OpenPose layout the video ControlNets were trained on: 18 body joints + 21-point hands, faces off by default. Across frames: identity tracking (IoU), visibility hysteresis (on > 0.3, off < 0.2) and a One-Euro filter per joint, so the skeleton does not flicker.--keypoints x.jsonwrites every skeleton (reshot-pose/1: stable id per person, 134 points + scores per frame).pip install "reshot[pose]"; weights (~340 MB) download once fromyzd-v/DWPose, or--checkpoint-dir. Measured: 306 ms/frame on an M2 Max CPU, the 12 s demo in 90 s. --pose-detect-every N(default 3). The detector is 80 % of the pose cost, so it runs every third frame and the previous skeletons supply the boxes in between; a cut or an unreliable skeleton re-detects at once. Against every-frame detection on the 289-frame demo: 280 frames identical people count, 80 % of joints within 2 px, 91 % within 5 px, 35 % faster.- Line output —
--control canny, thresholds--canny LOW,HIGH. No model. --control depth,pose,cannywrites all three in one go (-oa directory); one model load per kind.- Web page: a third choice, What to make — depth map / skeleton / lines; quality and the advanced fields show only for the type they apply to; the result panel names the file, offers the keypoints JSON for skeletons, and prints the prompt line for your target × type.
- Python:
write_rgb_video,reshot.pose(PoseClip,skeleton.render_frame,tracking.stabilise),reshot.edges.canny_frame;RunConfig.controland the pose / canny fields. - Colab notebook and
docs/AGENT_INSTALL.mdcover the new types. - Pose and canny are read at the output size (no "model resolution"), with their own, much smaller host-RAM estimate.
- Verified on MiniMax H3: the three demo takes re-made with the skeleton as
<Video 1>(same prompts and sheets) reproduce the six beats like the depth takes —docs/demo-pose.gif, prompts with seeds indocs/prompts/*_pose.txt. - Verified on MiniMax H3: the three demo takes re-made with the skeleton as
<Video 1>(same prompts and sheets) reproduce the six beats like the depth takes; prompts + seeds indocs/prompts/*_pose.txt, comparison indocs/img/pose_vs_depth_takes.jpg.
0.4.1 — 2026-09-14
- Colab notebook.
examples/reshot_colab.ipynb— a free GPU, upload a clip, downloaddepth.mp4, no install. "Open in Colab" badge in both READMEs. run(cfg, backend=...)accepts a pre-built backend, so a resident process (a server, a Space) loads the weights once instead of per clip. Without it nothing changes.demo/space/: a ZeroGPU Gradio app, ready for a Hugging Face account with billing enabled (Gradio Spaces are no longer free to host).demo/landing/: the static Space.- Discussions are open; the README has a Community section.
0.4.0 — 2026-09-12
- Web page.
reshotwith no arguments (orreshot web) starts a local UI in the browser: drop a clip, pick the target model and quality, run, preview reference and depth side by side, download, copy the prompt line for Seedance / MiniMax H3. Studio Air look (the Maosika design system), Chinese and English. Standard library only — no new dependencies; listens on 127.0.0.1; results in~/ReShot. Verified in Chrome with the real model.
0.3.8 — 2026-09-12
- Fix: on Apple Silicon with torch ≥ 2.14 the model failed to load with
invalid low watermark ratio 1.4— the MPS low watermark is now set alongside the high one. docs/AGENT_INSTALL.md: a step-by-step install guide written for AI coding agents, and a copy-paste prompt in the README that points them at it.
0.3.7 — 2026-09-12
- On PyPI:
pip install reshot(anduvx reshot …). No git needed any more.
0.3.6 — 2026-09-12
--quality fastis the default (the model sees 644×364 for 16:9, 364×644 for 9:16; ~3 GB VRAM, 34 ms/frame on a 3080 Ti).full(924×518 / 518×924, ~11 GB) is the user's choice; asking for it on a card under 11.5 GB prints a warning first.autois gone.- The run prints and records (
model_input_resolutionin metrics) the exact resolution the model works at;model_input_resolution()is public.
0.3.5 — 2026-09-12
--quality auto|full|fastreplaces the silent small-GPU fallback of 0.3.4:fullis 518 px,fast364 px,auto(default) picks by VRAM and says which it chose.--input-sizestays as the expert override. Measured difference full vs fast on the same clip: mean 5.3/255 grey levels, 95 % of pixels within 15, edge energy −4.5 % — fine detail only.
0.3.4 — 2026-09-12
- Small GPUs work out of the box. Measured on an RTX 3080 Ti: the default
--input-size 518peaks at 7.4 GiB allocated / 10.9 GiB reserved and OOMs on an 8 GB card; 364 peaks at 2.25 / 3.0 GiB. Cards under 11.5 GB now get 364 automatically (reported as avramstep, recorded asinput_size_usedin metrics); an explicit--input-sizeis always respected. - Metrics gain
gpu_peak_allocated_bytes/gpu_peak_reserved_bytes; hidden--cuda-memory-fractionemulates a smaller card for verification. - README: a "What you need" table with the measured numbers.
0.3.3 — 2026-09-12
- Memory estimate is now a measured line, not a guess: peak RSS = 2.0 GiB + 20 B × frames ×
processing pixels (fitted on six RTX 4090 runs, base 1.73 GiB / slope 16.9 B, residual
≤ 0.05 GiB, padded ~15 %). The old flat 32 B/pixel-frame over-refused long clips and
under-estimated short ones;
--max-framessuggestions now account for the base. - Measured on the same runs: 61–62 ms/frame on a 4090 for clips ≥ 190 frames (77–92 ms/frame for very short clips, where model load and the first window dominate).
0.3.2 — 2026-09-12
- Fix:
--max-resno longer lowers the inference resolution. It capped the processing size too, so--max-res 320fed the model a thumbnail; inference now always runs at model resolution and--max-resonly sizes the output (regression test added). - Batch mode:
reshot a.mp4 b.mp4 … -o dir/(or any-othat is a directory) runs every clip on one model load;--metrics/--npzbecome per-clip directories; a failed clip is skipped and reported. Python:run_many(). - Memory:
to_grayconverts frame by frame (−1.2 GB peak for a 12 s clip, byte-identical output); decoding writes into one preallocated buffer instead of list +np.stack(−400 MB). --npz/--metricscreate their parent directories.torch.load(weights_only=True); inference undertorch.inference_mode();extract()honoursRESHOT_FAKE_BACKEND.
0.3.1 — 2026-09-12
- Fix: the package failed to import on Windows since 0.2.0 (
import resourceis Unix-only); peak-memory metric now uses the Win32 counter there. - README rewritten as a manual: the problem → what it does → four steps with the real prompts and character sheets from the demo (
docs/prompts/,docs/refs/) → what transfers and what doesn't → presets → developers. - New demo: a corridor fight → depth map → three generated takes (two humans, one bear),
docs/demo-fight.gif+docs/demo-fight.mp4; social preview card updated. - Wording: the output is called what it is — a depth map (relative inverse depth, monocular
video depth estimation), no longer a "blockout" (that term means untextured 3D geometry).
Docs, CLI help, Space page and demo labels updated;
demo.make_blockout→make_depth_map.
0.3.0 — 2026-09-12
- Renamed: depthcat → ReShot. Package, CLI, env var and error class follow:
pip install git+https://github.com/maosika-ai/reshot,reshot in.mp4 -o out.mp4,RESHOT_FAKE_BACKEND,reshot.ReshotError. No behaviour change. - README/Space copy: who makes it — Maosika 猫斯卡, the AI short-drama production system.
0.2.1 — 2026-09-11
--target seedance: 24 fps, frame size a multiple of 16, ≤ 15 s, and a warning when the frame falls below the 407,696-pixel floor — all from the official Seedance reference-video spec.Target.min_pixelsand the matching pipeline warning.- README rewritten as a product page (Seedance first); Seedance recipe in the usage guide; demo default preset is now
seedance.
0.2.0 — 2026-09-11
- One pipeline:
reshot.run(RunConfig)is the single code path for the CLI and the Python API. - Backend registry (
vda,fake);--backend fakeruns the whole pipeline without a model. - Typed errors with exit codes (2 input · 3 RAM budget · 4 ffmpeg · 5 weights) and concrete fixes in the message.
RunConfigvalidates arguments before any work;plan()exposes what a run will do.- Metrics JSON now records the full config and plan.
- Lint (ruff) in CI; 28 tests without a model plus a real-model CPU smoke job.
0.1.0 — 2026-09-11
- First release:
reshot in.mp4 -o out.mp4on Video Depth Anything Small (Apache-2.0). - Depth estimated at model resolution, whole-clip normalisation, near = white, x264 CRF 12.
--target h3/wanpresets (fps, size multiple, max length),--npz,--metrics.- Host-RAM estimate with refusal over 50 % of physical RAM; MPS allocator cap on Apple Silicon.
- Measured: RTX 4090 fp16 70 ms/frame; Apple M2 Max fp32 ~500 ms/frame.