Communitygithub.com

film-crew

Tools used during a film run: backends dispatch job sheets (JSON specifying what to generate) to official video/image model APIs, viewer turns the run directory into web pages (live progress, showcase, node graph), comfyui opens each shot in ComfyUI for inspection, and formats define the interchange files (job sheet, shots manifest) with validation scripts. Use when you need to generate video or images from a job sheet, preview the exact request, select a model by its capability card (feeds, length, reference images, price, speed), watch live progress, view a showcase or node graph after generation, open shots in ComfyUI, or convert a run directory into a shots manifest.

What is film-crew?

film-crew is a modular toolkit for AI-driven film production that provides four parallel components—backends, viewer, comfyui, and formats—each with its own overview.md documentation. The backends module reads job sheets (JSON specifying what to generate) and sends them to official video/image model APIs (Alibaba Cloud Bailian for Wan 3.0, HappyHorse 1.1; Volcano Engine Ark for Seedance 2.5/2.0; MiniMax for H3-Max; OpenAI Images for gpt-image 2.6), reading API keys exclusively from environment variables (DASHSCOPE_API_KEY, ARK_API_KEY, MINIMAX_API_KEY, OPENAI_API_KEY). The viewer module transforms a run directory into three types of web pages: a live progress page showing every generation (including cost and time), a showcase page comparing input images, reference images, prompts, parameters, and output for each shot, and a node graph that can be exported to a ComfyUI workflow. The comfyui module opens each shot's data as a ready-to-run ComfyUI workflow for human inspection without re-generating. The formats module defines and validates two interchange files—the job sheet and the shots manifest—and provides scripts to read a run directory into a manifest. The entire toolkit only requires Python 3.10+ for most operations, with optional dependencies (Pillow, ffmpeg) for the showcase page. Design principles emphasize safety: dry-run requests before actual generation, read-only viewers, environment-only API keys, and validation of all output manifests.

Works with~Claude Code✓Codex CLI~Cursor
npx skills add https://github.com/memoryoffish/film-director-skill-plugin/tree/HEAD/plugins/film-crew

Ask in your favorite AI

Open a new chat with this agent skill pre-loaded.

Documentation

What does film-crew do?

In a nutshell: the filming methods determine "how to shoot"; here are the tools used during the shoot—select models, watch progress, present the finished work. Four parallel modules, each with its own overview.md; all paths are relative to this directory.

What each of the four modules does

ModuleWhat it doesWhen to useRead first
backends/Job sheets in, videos and images outTo generate a video or a set of images; to preview what request will be sent; to select a modelbackends/overview.md
viewer/Run directory → web pages for humansDuring a film run: watch each generation (progress page); after the run: see what each shot consumed and produced (showcase, node graph)viewer/overview.md
comfyui/Each shot placed into ComfyUIWhen a human wants to see in ComfyUI how a shot was built, and then reuse the key frames and outputscomfyui/overview.md
formats/Format specifications for two interchange filesTo write or validate a job sheet; to read a run directory into a shots manifestformats/overview.md

The four modules communicate only through two files: job sheet (specifies what to generate in one request, handed to the backend) and shots manifest (documents what each shot in a film used and produced, handed to the two viewers).

Where they appear during a film shoot

  1. Start the shoot: Launch the progress page inside a tmux session; every subsequent generation will be listed there—python3 viewer/scripts/progress.py <output directory> --jobs <project>/clips --prices backends/cards/prices.json --every 60.
  2. Generate: Each generation writes a job sheet into <project>/jobs/ (for video) or <project>/jobs_img/ (for images). First, python3 backends/scripts/filmgen.py request <sheet> to preview what will be sent, then run. The backends call the official APIs of each provider: Alibaba Cloud Bailian (Wan 3.0, HappyHorse 1.1), Volcano Engine Ark (Seedance 2.5 / 2.0), MiniMax (H3-Max), OpenAI Images (gpt-image 2.6). Which model to use is chosen via backends/cards/.
  3. Finish: Write a shot table meta.json in the run directory (each shot's name, its start and end timestamps in the finished film, which generation record was used), then run python3 formats/read_run.py <config> --out <manifest directory> to produce a shots manifest, and python3 formats/check_manifest.py to validate it.
  4. Present to the viewer: The web page is produced by python3 viewer/scripts/console.py <manifest…> <output directory>; to open in ComfyUI, run python3 comfyui/scripts/shots2comfy.py <manifest…> --comfy <ComfyUI directory>. The node graph on the web page follows the same workflow structure as ComfyUI; to include it, first run shots2comfy.py, then add --workflows to console.py.

Requirements: Python 3.10+. backends, formats, the progress page, and shots2comfy.py rely only on the standard library (backends uses ffprobe to measure output video duration); the showcase (console.py) additionally needs Pillow and ffmpeg; send requires SSH with tmux on the remote machine; ComfyUI node packages run within ComfyUI's own environment (using its bundled Pillow and numpy).

For the parameters of each step and what to check after each step, see that module's overview.md.

Rules

  • Keys are read from environment variables only (DASHSCOPE_API_KEY, ARK_API_KEY, MINIMAX_API_KEY, OPENAI_API_KEY); never written into any file, never printed. request works even without a key set.
  • Viewers are read-only: they do not modify the run directory and do not call generation APIs. If a human sees adjustments needed in ComfyUI or on the web page, they tell the agent, who makes changes and submits a new job.
  • Preview before sending: For every job sheet, run request first. To redo or change parameters, save the modified sheet under a new name.
  • Preview the generated page yourself before handing it over to the human.

Related Skills