Skip to content

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.

docs: web page screenshots (corridor demo clip) in README, HF Space page and PyPI text; scripts/shoot_web_ui.py drives headless Chrome over CDP

wangfengd60101e789e9
diff --git a/README.md b/README.md
index 8ba0611..988a0ab 100644
--- a/README.md
+++ b/README.md
@@ -59,6 +59,8 @@ on a short clip with --metrics and show me the numbers. Don't say it's done unti
**Easiest — the web page.** Type `reshot` with nothing after it: a page opens in your browser (everything stays on your computer). Drop the clip in, pick which model it is for, click **Make depth map**. You get the reference and the depth map side by side, the numbers, a download button, and the prompt line to paste into Seedance or MiniMax H3.
+<p align="center"><img src="docs/img/web_ui_en.jpg" width="720" alt="the ReShot web page: reference clip and depth map side by side, target and quality on the right"></p>
+
```bash
reshot # opens http://127.0.0.1:8765 — results land in ~/ReShot
reshot web --port 9000 --out ./depth --no-browser # options, if you want them
diff --git a/README.zh-CN.md b/README.zh-CN.md
index 6b94874..3d38311 100644
--- a/README.zh-CN.md
+++ b/README.zh-CN.md
@@ -59,6 +59,8 @@ depth.mp4 没生成出来之前不要说完成。
**最省事——网页。** 只敲 `reshot`,后面什么都不加,浏览器会打开一个页面(所有处理都在你自己电脑上)。把片子拖进去,选给哪家模型用,点**生成深度图**。参考片和深度图并排预览,数字、下载按钮、要粘到 Seedance 或 MiniMax H3 的提示词都在同一屏。
+<p align="center"><img src="docs/img/web_ui_zh.jpg" width="720" alt="ReShot 网页:左边参考片与深度图并排,右边选模型和画质"></p>
+
```bash
reshot # 打开 http://127.0.0.1:8765,结果存到 ~/ReShot
reshot web --port 9000 --out ./depth --no-browser # 想改端口 / 目录 / 不自动开浏览器
diff --git a/demo/space/index.html b/demo/space/index.html
index c3dc3ea..5106ee1 100644
--- a/demo/space/index.html
+++ b/demo/space/index.html
@@ -36,7 +36,11 @@
<p class="cap">top: the reference and its depth map · bottom: three takes generated from that depth map — two women, one rabbit; same moves, same camera<br><span class="zh">上排:参考片和它的深度图 · 下排:用这张深度图生成的三段片——两个女人、一只兔子;动作一样,镜头一样</span></p>
<pre><code>pip install reshot
-reshot reference.mp4 -o depth.mp4 --target seedance</code></pre>
+reshot # opens a page in your browser — drop the clip in, click, download
+reshot reference.mp4 -o depth.mp4 --target seedance # or the command line</code></pre>
+
+<img class="demo" src="web_ui.jpg" alt="the ReShot web page: reference clip and depth map side by side, target and quality on the right" loading="lazy">
+<p class="cap">The web page (<code>reshot</code> with nothing after it): everything runs on your own computer; the prompt line for Seedance or MiniMax H3 is right there to copy.<br><span class="zh">网页版(只敲 <code>reshot</code>):全部在你自己电脑上跑;给 Seedance / MiniMax H3 的提示词就在旁边,点一下复制。</span></p>
<div class="row">
<a class="btn" href="https://github.com/maosika-ai/reshot">GitHub · code &amp; docs</a>
@@ -56,7 +60,7 @@ reshot reference.mp4 -o depth.mp4 --target seedance</code></pre>
<h2>How to use it <span class="zh">/ 怎么用</span></h2>
<table>
<tr><td><b>1</b></td><td><code>pip install reshot</code> — or paste into Claude Code / Codex: <i>"Install reshot from PyPI following https://raw.githubusercontent.com/maosika-ai/reshot/main/docs/AGENT_INSTALL.md and run a test clip"</i>. ComfyUI: install <a href="https://github.com/maosika-ai/ComfyUI-ReShot">ComfyUI-ReShot</a>.<br><span class="zh">装;或者把这句粘给 Claude Code / Codex 让它装;ComfyUI 用户装节点包</span></td></tr>
-<tr><td><b>2</b></td><td><code>reshot reference.mp4 -o depth.mp4 --target seedance</code> — 24 fps, H.264, the Seedance reference-video spec out of the box; <code>--target h3</code> for MiniMax H3.<br><span class="zh">抽深度图;<code>--target seedance</code> 直接按 Seedance 参考视频规格出片</span></td></tr>
+<tr><td><b>2</b></td><td>Type <code>reshot</code> — a page opens in your browser: drop the clip in, pick Seedance or MiniMax H3, click, download. Or the command line: <code>reshot reference.mp4 -o depth.mp4 --target seedance</code> — 24 fps, H.264, the Seedance reference-video spec out of the box.<br><span class="zh">敲 <code>reshot</code> 打开网页:拖进去、选模型、点一下、下载。或者命令行 <code>--target seedance</code> 直接按 Seedance 参考视频规格出片</span></td></tr>
<tr><td><b>3</b></td><td><b>Seedance 2.0 / 2.5:</b> upload <code>depth.mp4</code> as a reference video and prompt <code>参考@视频1的动作与运镜,顺序与视频保持一致。</code> + the people and the look.<br><b>MiniMax H3:</b> attach it as <code>&lt;Video 1&gt;</code>, a character sheet as <code>&lt;Picture 1&gt;</code>; define <code>&lt;Video 1&gt;</code> as "the fight choreography and camera movement shown in &lt;Video 1&gt;, a grey depth map…" and state that "its grey depth look is not transferred". The full prompts for the three takes are in <a href="https://github.com/maosika-ai/reshot/tree/main/docs/prompts">docs/prompts</a>.<br><span class="zh">交给模型:Seedance 当参考视频上传并写「参考@视频1的动作与运镜」;MiniMax H3 挂成 &lt;Video 1&gt;、定妆图挂 &lt;Picture 1&gt;,明说灰色外观不要抄。三段片的完整提示词在 docs/prompts。</span></td></tr>
<tr><td><b>4</b></td><td>Same six shots, same camera, your cast — the three takes above. Tips that made them work: keep the reference under 15 s; for MiniMax H3 shrink the depth map (<code>--max-res 320</code>) so the grey silhouette doesn't pull the face shape; keep the size ratio between characters as the depth map has it.<br><span class="zh">出片。几条经验:参考片 15 秒以内;给 MiniMax H3 的深度图缩到 320(不然灰影会带脸型);角色体量比例别跟深度图打架。</span></td></tr>
</table>
diff --git a/demo/space/web_ui.jpg b/demo/space/web_ui.jpg
new file mode 100644
index 0000000..b4c40c7
Binary files /dev/null and b/demo/space/web_ui.jpg differ
diff --git a/docs/PYPI.md b/docs/PYPI.md
index 2e613c3..1ae6c0f 100644
--- a/docs/PYPI.md
+++ b/docs/PYPI.md
@@ -6,9 +6,11 @@ ReShot turns a reference video into a depth-map video (near = white, far = black
```bash
pip install reshot
-reshot reference.mp4 -o depth.mp4 --target seedance
+reshot # web page: opens in your browser, drop the clip in
+reshot reference.mp4 -o depth.mp4 --target seedance # or the command line
```
+- **Web page** (`reshot` with nothing after it): everything runs on your computer; reference and depth map side by side, download, and the prompt line for Seedance / MiniMax H3 to copy.
- Presets for **Seedance 2.0 / 2.5** reference video (`--target seedance`), **MiniMax H3** (`h3`), **Wan 2.1 VACE** (`wan`).
- `--quality fast` (default; the model sees 644×364 for 16:9, ~3 GB VRAM) or `full` (924×518, ~11 GB).
- Depth normalised once over the whole clip — no flicker; frames picked by timestamp; sizes cropped to the model's grid, never padded.
diff --git a/docs/img/web_ui_en.jpg b/docs/img/web_ui_en.jpg
new file mode 100644
index 0000000..b4c40c7
Binary files /dev/null and b/docs/img/web_ui_en.jpg differ
diff --git a/docs/img/web_ui_zh.jpg b/docs/img/web_ui_zh.jpg
new file mode 100644
index 0000000..fb82a1b
Binary files /dev/null and b/docs/img/web_ui_zh.jpg differ
diff --git a/scripts/shoot_web_ui.py b/scripts/shoot_web_ui.py
new file mode 100644
index 0000000..d4fe0d0
--- /dev/null
+++ b/scripts/shoot_web_ui.py
@@ -0,0 +1,118 @@
+"""Screenshot the web page for the README — drives headless Chrome over the DevTools protocol.
+
+Why not Playwright: it downloads its own browser; Chrome is already installed and
+`websockets` is enough to talk to it. Usage (server already running on --url):
+
+ python scripts/shoot_web_ui.py --video 走廊武打.mp4 --out docs/img/web_ui.jpg
+"""
+
+from __future__ import annotations
+
+import argparse
+import asyncio
+import base64
+import json
+import subprocess
+import time
+import urllib.request
+from pathlib import Path
+
+import websockets
+
+CHROME = "/Applications/Google Chrome.app/Contents/MacOS/Google Chrome"
+
+
+async def shoot(url: str, video: Path, out: Path, width: int, height: int, lang: str) -> None:
+ port = 9333
+ proc = subprocess.Popen(
+ [
+ CHROME,
+ "--headless=new",
+ f"--remote-debugging-port={port}",
+ "--no-first-run",
+ f"--window-size={width},{height}",
+ "--hide-scrollbars",
+ f"--user-data-dir=/tmp/reshot-shoot-profile",
+ "about:blank",
+ ],
+ stdout=subprocess.DEVNULL,
+ stderr=subprocess.DEVNULL,
+ )
+ try:
+ for _ in range(50):
+ try:
+ tabs = json.load(urllib.request.urlopen(f"http://127.0.0.1:{port}/json"))
+ break
+ except Exception:
+ time.sleep(0.2)
+ ws_url = next(t["webSocketDebuggerUrl"] for t in tabs if t["type"] == "page")
+ async with websockets.connect(ws_url, max_size=2**30) as ws:
+ n = 0
+
+ async def call(method, **params):
+ nonlocal n
+ n += 1
+ await ws.send(json.dumps({"id": n, "method": method, "params": params}))
+ while True:
+ msg = json.loads(await ws.recv())
+ if msg.get("id") == n:
+ if "error" in msg:
+ raise RuntimeError(msg["error"])
+ return msg["result"]
+
+ async def js(expr):
+ r = await call("Runtime.evaluate", expression=expr, returnByValue=True, awaitPromise=True)
+ return r["result"].get("value")
+
+ await call(
+ "Emulation.setDeviceMetricsOverride", width=width, height=height, deviceScaleFactor=2, mobile=False
+ )
+ await call("Page.enable")
+ await call("DOM.enable")
+ await call("Page.navigate", url=url)
+ await asyncio.sleep(1.0)
+ print("page:", await js("location.href + ' | ' + document.title + ' | ' + document.readyState"))
+ if lang == "en":
+ await js("document.getElementById('lang').click()")
+ obj = None
+ for _ in range(50): # the page must have settled before the input exists
+ r = await call("Runtime.evaluate", expression="document.getElementById('file')")
+ if r["result"].get("objectId"):
+ obj = r["result"]["objectId"]
+ break
+ await asyncio.sleep(0.2)
+ await call("DOM.setFileInputFiles", files=[str(video.resolve())], objectId=obj)
+ for _ in range(100):
+ if await js("!document.getElementById('players').hidden"):
+ break
+ await asyncio.sleep(0.2)
+ await js("document.getElementById('run').click()")
+ for _ in range(600):
+ if await js("!document.getElementById('result').hidden"):
+ break
+ await asyncio.sleep(0.5)
+ await asyncio.sleep(1.5) # let both players show a frame
+ await js("document.querySelectorAll('video').forEach(v => { v.pause(); v.currentTime = 2.0; })")
+ await asyncio.sleep(1.0)
+ shot = await call("Page.captureScreenshot", format="jpeg", quality=88, captureBeyondViewport=True)
+ out.parent.mkdir(parents=True, exist_ok=True)
+ out.write_bytes(base64.b64decode(shot["data"]))
+ print("wrote", out, out.stat().st_size, "bytes")
+ finally:
+ proc.terminate()
+
+
+def main() -> None:
+ ap = argparse.ArgumentParser()
+ ap.add_argument("--url", default="http://localhost:8765/")
+ ap.add_argument("--video", required=True, type=Path)
+ ap.add_argument("--out", required=True, type=Path)
+ ap.add_argument("--width", type=int, default=1360)
+ ap.add_argument("--height", type=int, default=980)
+ ap.add_argument("--lang", choices=["zh", "en"], default="zh")
+ a = ap.parse_args()
+ asyncio.run(shoot(a.url, a.video, a.out, a.width, a.height, a.lang))
+
+
+if __name__ == "__main__":
+ main()