find-movie-clips

--- name: find-movie-clips description: >- Find the video clip of a movie or TV scene and turn it into a clean reference take for an AI remake, a parody, an edit or a motion-control run. Covers which clip database to open for what you know (a quote, a film and scene, a look, a character), which of them an agent may fetch and which only a person may open, a tested yt-dlp search and download, cutting ten seconds straight out of a public-domain film on the Internet Archive, a script that splits a scene into its uncut takes with a contact sheet per take, the rules for a take a video model can follow (one take, one person, real movement, 720p or more) and what to check about rights before using it. Use when someone asks where to find movie clips, film scene references, a scene by its quote, scene packs, "the clip where he says X", a reference video for Seedance, Kling Motion Control, MiniMax Recast or Higgsfield Genjutsu, or says their remake source has cuts, watermarks or black bars. For still frames and look references use find-references; for the remake itself use scene-recast-video. license: MIT metadata: author: vargHQ version: "1.1.0" openclaw: requires: anyBins: - yt-dlp - ffmpeg homepage: https://varg.ai/how-to compatibility: >- No key. Needs yt-dlp, ffmpeg, ffprobe, curl, jq and bc on the machine. The clip databases marked "person" are opened by the person in a browser, not by the agent. allowed-tools: Bash(yt-dlp:*) Bash(ffmpeg:*) Bash(ffprobe:*) Bash(curl:*) Bash(jq:*) Bash(bash:*) Read Write --- # Find movie clips: the scene, the clean take, the rights A remake is only as good as its reference clip. Still-frame libraries (ShotDeck, Film-Grab, Shot Cafe) give you a look, not motion; for a video reference you need a clip database, a download and a cut down to one usable take. Everything marked "tested" below was run on 2026-11-13. ## 1. Ask, then go - **What do they know about the scene?** A line of dialogue, the film and the moment, only a look or a move, or one character across a whole show. This picks the database (section 2). - **What is it for?** A video reference for a model (needs one uncut take, 5 to 30 s), a quote for an edit, or a mood reference. - **Where will the result be posted?** Decides how much the rights section (7) matters. ## 2. Pick the database by what you know | You know | Open | What you get | Who opens it | |---|---|---|---| | The line | [PlayPhrase.me](https://www.playphrase.me) | Every place in films and series where the phrase is said, played back to back. Free. | person | | The line, and you need a file | [Clip.cafe](https://clip.cafe) | Search by quote or film; longer scenes than Yarn, with a download. | person | | The line, as a short reaction | [Yarn](https://getyarn.io) | A few seconds around the quote. Too short for a remake, right for a meme. | person | | The film and the moment | YouTube: Movieclips and channels like it | Two to four minute scenes, 720p or 1080p. | agent (section 3) | | A look, a move, a kind of shot | [Flim](https://flim.ai) | Search in plain words across stills and video clips from films, ads and music videos. | person | | The name of a technique | Eyecannndy | Short excerpts sorted by visual technique. | person | | One character, every scene | Scene packs | Fan editors cut all scenes of a character in 4K and share them from Instagram accounts (a MEGA link in the caption), Google Drive folders and YouTube. Search `<character> scene pack 4k`. | person | | An old film, with no rights question | [Internet Archive](https://archive.org/details/feature_films) | Whole public-domain films, cut by time code without downloading the file. | agent (section 4) | Who says so: Clip.cafe as "longer scenes" against Yarn's "super short" clips ([@graceea29887132](https://x.com/graceea29887132/status/2105729889030574170)); PlayPhrase ([@malummiivt](https://x.com/malummiivt/status/2027822155426103388), 1,577 bookmarks); Flim's "1.5M stills and 400K video clips" ([@xpg0970](https://x.com/xpg0970/status/2074264672887595432)); scene packs ([@kawaiidinof](https://x.com/kawaiidinof/status/2121220961944948980), [@xaurorasxo](https://x.com/xaurorasxo/status/1979304680116064346)). Counts are the posters' claims. **Why "person":** tested with a plain request. Clip.cafe's `robots.txt` disallows AI crawlers by name (`anthropic-ai`, `cohere-ai`, `CCBot`, `Bytespider`). Yarn and Eyecannndy answer automation with HTTP 403. PlayPhrase and Flim are browser apps with accounts. For these the agent names the site and the words to search, the person opens it and hands back a file or a YouTube link. Do not fetch them with a changed user agent. ## 3. The agent route: search YouTube, read the list, download once ```bash # 1. search with metadata, no download yt-dlp "ytsearch8:<film> <year> <the line or the moment> scene" --flat-playlist \ --print "%(id)s | %(duration)s | %(view_count)s | %(channel)s | %(title)s" # 2. download the one you picked at 720p with sound yt-dlp -f "bv*[height<=720][ext=mp4]+ba[ext=m4a]/b[height<=720]" --merge-output-format mp4 \ -o "scene.%(ext)s" "https://www.youtube.com/watch?v=<id>" ``` How to read the list (tested on one scene, eight results): - **Take the 2 to 4 minute upload from a clip channel** (Movieclips, Binge Society): it holds the whole scene in the film's own cut. The 8 s and 27 s results are memes of one line, often re-cropped. - **Be wary of uploads much longer than the scene** (one result ran 7 minutes for a 3 minute scene): they add commentary or other scenes. - **720p is enough.** Video models take 720p plates; a 480p plate was refused as invalid input in our run (`scene-recast-video`). - One download per scene. Links from X, TikTok, Instagram and 1,800 other sites: `media-download`. ## 4. Public-domain films: cut straight from the Internet Archive ```bash # 1. find items; ask for 30, because the most downloaded ones are old 480p uploads curl -s "https://archive.org/advancedsearch.php?q=title%3A%28<title>%29+AND+mediatype%3Amovies&fl%5B%5D=identifier&fl%5B%5D=title&fl%5B%5D=licenseurl&sort%5B%5D=downloads+desc&rows=30&output=json" # 2. list an item's video files: name | resolution | seconds | bytes | original or derivative curl -s "https://archive.org/metadata/<identifier>" | jq -r '.files[] | select(.name|test("(mp4|mkv|mpeg|avi)$")) | "\(.name) | \(.width)x\(.height) | \(.length) | \(.size) | \(.source)"' # 3. find the moment: one frame every 2 minutes from the small mp4, tiled for t in $(seq 0 120 5400); do ffmpeg -v error -ss $t -i "$SMALL_URL" -frames:v 1 -vf scale=320:-2 "scout_$(printf %04d $t).jpg"; done ffmpeg -v error -pattern_type glob -i "scout_*.jpg" -vf tile=8x6 scout.jpg # read it, pick the minutes # 4. cut up to 3 minutes around it from the best file, without downloading the film ffmpeg -ss 1770 -t 180 -i "$BEST_URL" -map 0:v:0 -map 0:a:0? -map_chapters -1 \ -c:v libx264 -crf 18 -pix_fmt yuv420p -c:a aac cut.mp4 ``` The file URL is `https://archive.org/download/<identifier>/<file name>`, with the name URL-encoded (spaces as `%20`, brackets as `%5B` `%5D`). Tested twice (once by a fresh agent following this page): ten seconds at 1920x1080 out of a 1.8 GB file arrived in 6 s; a 3 minute cut took 46 s; 31 scout frames took 8 s. What the runs taught: - **The `.mp4` is usually the Archive's own downscaled copy** (`derivative`, 480p). The HD file is the `original`, often an `.mkv`. Read the resolution column, not the file name: a file named `1080p` was 640x480. - **The best item is rarely on top.** The 720p item was result 26 of 30 by downloads. - **Licence:** `licenseurl` is set by the uploader. Pass: a public-domain mark or CC0 (`publicdomain/mark`, `publicdomain/zero`, `licenses/publicdomain`) on a film that is itself known to be public domain. Not a pass: no field, or a `by-nc` or `by-nd` licence. A public-domain mark on a recent film is an uploader's mistake. - **Write down film time.** The time code that matters for the source note is the `-ss` offset plus the take's start inside the cut. ## 5. What a model can follow | Rule | Why | Source | |---|---|---| | One continuous take, no cuts | Cuts make the model lose who is who, or it truncates the clip | Kling guide; [@everestchris6](https://x.com/everestchris6/status/2107135574469746896) | | One person on screen most of the time, face and upper body visible | With two people only the larger or nearer one is followed | Kling guide; Higgsfield blog | | Real movement | "If the camera sits still and the person barely moves, you get the same flat shot in a new costume" | Calixte LeBlanc, YouTube | | 5 to 30 s, and no longer than you need | Tools cap at 30 s and the price follows the length | tool limits | | Empty hands, nobody crossing in front | A held prop is read as part of the body. If the scene is about the prop (a phone call), keep it and name the prop in the remake prompt | Higgsfield blog | | A clean copy | Burned-in subtitles and logos are copied into the remake; find the clean original instead of erasing them | [@everestchris6](https://x.com/everestchris6/status/2107135574469746896) | ## 6. Split the scene into takes, then choose ```bash bash scripts/takes.sh scene.mp4 8 30 takes # min seconds, max seconds, out dir ``` Run it by its path inside this skill's folder; the output folder can be anywhere. It finds every cut (`ffmpeg` scene detection at 0.3), prints the uncut takes, and for each one of at least the minimum length writes `take_NN.mp4` and `take_NN.jpg` (a frame every 1.5 s, ten at most). A take longer than the maximum is kept as its first seconds and marked `(first 30 s kept)`. Look at the sheets, or give them to a vision model, and choose by section 5. After any further trim, make the sheet again: a second person can enter in the last two seconds. Tested on a 3 min 24 s scene from a clip channel: 34 cuts, 8 takes of 8 s or more, the longest 17.8 s. What the sheets showed, and what to do about each: - **The last "take" was the channel's end card** (subscribe panel, 31 s). Drop the final take of any clip-channel upload. - **A channel logo is burned into a corner.** Crop it out if the frame allows, or find another upload; it will be redrawn in your remake otherwise. - **Black bars at the sides** (a 4:3 film in a 16:9 file). Find and remove them: ```bash ffmpeg -ss 2 -t 4 -i take_01.mp4 -vf cropdetect=24:2:0 -f null - 2>&1 | grep -o "crop=[0-9:]*" | sort | uniq -c | sort -rn | head -1 ffmpeg -i take_01.mp4 -vf "crop=1060:720:60:0" -c:v libx264 -crf 18 -c:a copy take_01_clean.mp4 ``` - **A take can start with two people and end with one.** Trim to the part with one: `ffmpeg -ss 7 -t 6 -i take_01.mp4 ...`. - **Fights and handheld chaos fail rule 2** even when uncut: bodies overlap and faces leave the frame. A dialogue scene rarely has one take over 10 s. If no take passes, pick another scene, or a moment where one character speaks or moves alone. ## 7. Rights and filters: check before the work, not after - **A film clip is someone's copyright.** Parody that changes the meaning has a fair-use argument in the US; it is an argument, not a licence, and other countries are stricter. Client work and ads need a licensed or public-domain source. - **Platforms act on the soundtrack and on known footage.** Creators report film and TV sources "get claimed and muted" more than phone footage ([@everestchris6](https://x.com/everestchris6/status/2107135574469746896)). - **Video models refuse known footage and real faces.** A refused job means the provider said no to this input. Change the scene (a public-domain film, your own footage, an original scene in the same style); do not look for a setting that slips it through. - **Real actors are real people.** Their face and voice are theirs: recast with invented characters, and do not clone an actor's voice. - **Label the result** as AI-made and as parody where you post it. - **Scene packs and full-film downloads** are other people's copies of copyrighted films. This skill names them because editors use them; it does not fetch them. Safest order of sources: your own footage, licensed stock, a public-domain film (section 4), then a short clip of a known scene for commentary or parody. ## 8. Hand over Give the next step one folder: `take.mp4` (one take, 720p or more, clean), `sheet.jpg` (made from the final trim) and `source.txt`: ``` film: <title> (<year>) source: <link to the item or video> file: <file name> film time: 00:31:03 to 00:31:15 licence: <the licence field, or "copyrighted, used for parody"> in the take: <who, doing what>; rules not met: <none, or which> ``` Then: - `scene-recast-video`: recast the take with your own characters. - `ai-parody-video`: the joke and the format around it. - `find-references`: still frames for the look, from the libraries this skill does not cover. ## Sources Posts and guides read on 2026-11-12 and 2026-11-13: [@everestchris6](https://x.com/everestchris6/status/2107135574469746896) (how remake sources are chosen and checked), [@malummiivt](https://x.com/malummiivt/status/2027822155426103388), [@graceea29887132](https://x.com/graceea29887132/status/2105729889030574170), [@xpg0970](https://x.com/xpg0970/status/2074264672887595432), [@tgprovod](https://x.com/tgprovod/status/1969851511476736000), [@kawaiidinof](https://x.com/kawaiidinof/status/2121220961944948980), the [Kling Motion Control guide](https://kling.ai/quickstart/motion-control-user-guide), the [Higgsfield character swap guide](https://higgsfield.ai/blog/AI-Face-Character-Swap-in-Video-Photo-PRO-Guide). The commands and `scripts/takes.sh` were run on a public-domain scene; the databases marked "person" were not searched by the agent.

存档时间线

版本索引永久保留；内容副本只保留最新 1 份，更早版本仅留索引与哈希（存档时间线的证据链不会因此断裂）。

下载存档内容副本