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
community: Discussions, issue chooser, depth-quality template, Community section in both READMEs
wangfeng33b02f3a5d3d
diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.ymlnew file mode 100644index 0000000..7583cac--- /dev/null+++ b/.github/ISSUE_TEMPLATE/config.yml@@ -0,0 +1,11 @@+blank_issues_enabled: true+contact_links:+ - name: The video model didn't follow my depth map+ url: https://github.com/maosika-ai/reshot/discussions/categories/q-a+ about: Usually the prompt, not the depth map. Post a frame and the prompt in Q&A and we'll look.+ - name: Show what you made+ url: https://github.com/maosika-ai/reshot/discussions/2+ about: Reference, depth map, take, prompt line — the best ones get linked from the README.+ - name: Ask for a preset or a new output+ url: https://github.com/maosika-ai/reshot/discussions/categories/ideas+ about: Another video model, pose or edge output, a new platform — say which and why.diff --git a/.github/ISSUE_TEMPLATE/depth_quality.md b/.github/ISSUE_TEMPLATE/depth_quality.mdnew file mode 100644index 0000000..5e569bf--- /dev/null+++ b/.github/ISSUE_TEMPLATE/depth_quality.md@@ -0,0 +1,13 @@+---+name: Depth map looks wrong+about: Flat, flickering, inverted, or something is missing from the grey video+labels: question+---++**What looks wrong** (one sentence — e.g. "the person is the same grey as the wall", "flickers every few frames")++**One reference frame and the matching depth frame** (drag both in)++**Command or web-page settings** (target · quality · clip both ends %)++**Clip**: resolution · fps · length · was it a phone recording, a screen recording, or a generated video?diff --git a/CONTRIBUTING.md b/CONTRIBUTING.mdindex 1514149..934a74f 100644--- a/CONTRIBUTING.md+++ b/CONTRIBUTING.md@@ -33,3 +33,7 @@ CI runs the same on Ubuntu and Windows, plus the model smoke on CPU.Include: OS, GPU/CPU, `python -c "import torch;print(torch.__version__)"`, the exact command,and the stderr output with `-v`. If a clip reproduces it and you can share it, link it.++## Where to talk++Questions and results go to [Discussions](https://github.com/maosika-ai/reshot/discussions); bugs go to issues. If you want to take on something larger than a good-first-issue (pose output, a new backend), open a thread in Ideas first so we can agree on the shape before you build.diff --git a/README.md b/README.mdindex 94d8484..8bf3e50 100644--- a/README.md+++ b/README.md@@ -5,7 +5,7 @@<p align="center"><img src="docs/demo-fight.gif" width="720" alt="a fight scene, its depth map, and three new takes generated from it"></p><p align="center"><sub>Top: the reference and its depth map. Bottom: three takes generated from that depth map — two women, one rabbit. Same moves, same camera. <a href="docs/demo-fight.mp4">Full-resolution clip</a>.</sub></p>-<p align="center"><a href="README.zh-CN.md">中文</a> · <a href="docs/USAGE.md">User guide</a> · <a href="https://github.com/maosika-ai/ComfyUI-ReShot">ComfyUI nodes</a> · <a href="https://huggingface.co/spaces/maosika/reshot">Hugging Face</a> · <a href="CHANGELOG.md">Changelog</a></p>+<p align="center"><a href="README.zh-CN.md">中文</a> · <a href="docs/USAGE.md">User guide</a> · <a href="https://github.com/maosika-ai/ComfyUI-ReShot">ComfyUI nodes</a> · <a href="https://huggingface.co/spaces/maosika/reshot">Hugging Face</a> · <a href="https://github.com/maosika-ai/reshot/discussions">Community</a> · <a href="CHANGELOG.md">Changelog</a></p><p align="center"><a href="https://github.com/maosika-ai/reshot/actions/workflows/ci.yml"><img src="https://github.com/maosika-ai/reshot/actions/workflows/ci.yml/badge.svg" alt="ci"></a><a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue.svg" alt="Apache-2.0"></a>@@ -174,6 +174,13 @@ Three details make the output something a video model will actually follow:The model is Video Depth Anything Small (ByteDance, CVPR 2025). It works on overlapping 32-frame windows and aligns them, so depth doesn't jitter between frames. A 12-second 720p clip peaks at 3.9 GB of host RAM and 11 GB of VRAM (3 GB with `--input-size 364`) (measured; the estimate the tool shows before starting is a fitted line, within 0.05 GB of measurements) and it refuses up front if a clip won't fit. A `fake` backend runs the whole pipeline without a model for your own tests. Errors that are yours to fix are `ReshotError` subclasses with an exit code and a concrete fix in the message.+## Community++- **Made something?** Post the reference, the depth map, the take and your prompt line in [Show and tell](https://github.com/maosika-ai/reshot/discussions/2). The best ones get linked here.+- **The model didn't follow the depth map?** Ask in [Q&A](https://github.com/maosika-ai/reshot/discussions/categories/q-a) with one frame and the prompt — it is usually the prompt.+- **Something broke?** [Open an issue](https://github.com/maosika-ai/reshot/issues/new/choose). We answer within a day.+- **Want to help?** Start with a [good first issue](https://github.com/maosika-ai/reshot/labels/good%20first%20issue): a preset for another model, a Colab notebook, a README in your language. Pose output is the big one — see [#6](https://github.com/maosika-ai/reshot/issues/6).+## LicenseApache-2.0, and so is the default model. The vendored model code is under `reshot/third_party/`. Use it in a product, a pipeline, a service. The larger research-only weights (Base, Large) are CC-BY-NC and never load unless you ask for them.diff --git a/README.zh-CN.md b/README.zh-CN.mdindex f6c3934..8571c18 100644--- a/README.zh-CN.md+++ b/README.zh-CN.md@@ -5,7 +5,7 @@<p align="center"><img src="docs/demo-fight.gif" width="720" alt="一段武打参考片、它的深度图、用深度图生成的三段新武打片"></p><p align="center"><sub>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。<a href="docs/demo-fight.mp4">高清原片</a>。</sub></p>-<p align="center"><a href="README.md">English</a> · <a href="docs/USAGE.zh-CN.md">使用手册</a> · <a href="https://github.com/maosika-ai/ComfyUI-ReShot">ComfyUI 节点</a> · <a href="https://huggingface.co/spaces/maosika/reshot">Hugging Face</a> · <a href="CHANGELOG.md">更新日志</a></p>+<p align="center"><a href="README.md">English</a> · <a href="docs/USAGE.zh-CN.md">使用手册</a> · <a href="https://github.com/maosika-ai/ComfyUI-ReShot">ComfyUI 节点</a> · <a href="https://huggingface.co/spaces/maosika/reshot">Hugging Face</a> · <a href="https://github.com/maosika-ai/reshot/discussions">社区</a> · <a href="CHANGELOG.md">更新日志</a></p><p align="center"><a href="https://github.com/maosika-ai/reshot/actions/workflows/ci.yml"><img src="https://github.com/maosika-ai/reshot/actions/workflows/ci.yml/badge.svg" alt="ci"></a><a href="LICENSE"><img src="https://img.shields.io/badge/license-Apache--2.0-blue.svg" alt="Apache-2.0"></a>@@ -174,6 +174,13 @@ run(RunConfig(input=Path("参考片.mp4"), output=Path("深度图.mp4"), target=模型是 Video Depth Anything Small(字节跳动,CVPR 2025),以 32 帧为一个窗口重叠推理并对齐,深度不会一帧一帧地跳。12 秒 720p 一段片峰值占 3.9 GB 内存、11 GB 显存(`--input-size 364` 时 3 GB)(实测;开跑前显示的估算是拟合出来的直线,与实测误差 0.05 GB 以内),放不下会在开始之前拒绝。`fake` 后端不加载模型就能跑完整条流水线,方便你写测试。属于「用户该修」的错误都是 `ReshotError` 的子类,带退出码和具体的修法。+## 社区++- **做出片了?** 把参考片、深度图、成片和你的提示词那一行发到 [作品分享](https://github.com/maosika-ai/reshot/discussions/2),好的会链到这里。+- **模型没照深度图走?** 到 [问答区](https://github.com/maosika-ai/reshot/discussions/categories/q-a) 贴一帧画面和提示词——多半是提示词的事。+- **出错了?** [提 issue](https://github.com/maosika-ai/reshot/issues/new/choose),一天内回复。+- **想搭把手?** 从 [good first issue](https://github.com/maosika-ai/reshot/labels/good%20first%20issue) 开始:给别的模型加预设、写个 Colab、翻译 README。骨骼输出是最大的一件,见 [#6](https://github.com/maosika-ai/reshot/issues/6)。+## 协议Apache-2.0,默认模型也是。模型代码 vendored 在 `reshot/third_party/`。用在产品、流水线、服务里都行。更大的研究用权重(Base、Large)是 CC-BY-NC,不主动指定不会加载。