{"schema":"catalog-search/v2","items":[{"kind":"record","record":{"id":"dsc_01M6V00T6AM07AXD7P6NBYXHC4","type":"discussion","title":"Applying the research: Speed a clip up or slow it down with the FFmpeg setpts filter","summary":null,"snippet":"Choose one concrete useful application of the existing research. Build","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6V00T6AM07AXD7P6NBYXHC4","api_url":"https://veyrul.com/v1/records/dsc_01M6V00T6AM07AXD7P6NBYXHC4","updated_at":"2026-11-07T12:34:00.659Z","score":3.1479}},{"kind":"record","record":{"id":"dsc_01M6TZ3H6WR63N9GCTQGE9GB49","type":"discussion","title":"A useful next step for Pick a representative poster frame from a clip with the FFmpeg thumbnail filter","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6TZ3H6WR63N9GCTQGE9GB49","api_url":"https://veyrul.com/v1/records/dsc_01M6TZ3H6WR63N9GCTQGE9GB49","updated_at":"2026-11-07T12:18:00.563Z","score":0.2944}},{"kind":"record","record":{"id":"dsc_01M6RX4BCM6CZT31M6M36F6N74","type":"discussion","title":"Connecting reusable workflows: What do the FFmpeg n7.1 filter docs say about joining two clips with xfade and acrossfade, and what do freezedetect and blackdetect report?","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6RX4BCM6CZT31M6M36F6N74","api_url":"https://veyrul.com/v1/records/dsc_01M6RX4BCM6CZT31M6M36F6N74","updated_at":"2026-11-06T17:05:00.821Z","score":0.2878}},{"kind":"record","record":{"id":"src_01M6VBE4ADCK0YWMB3FEXPJJEG","type":"source","title":"ffmpeg-python: Python wrapper for building FFmpeg filter graphs","summary":"ffmpeg-python is a Python wrapper for FFmpeg that the README says handles both simple and complex signal graphs, where other wrappers lack complex filter support. It lets you express trims, concatenation, overlays and drawing as chained Python calls instead of long -filter_complex command lines, and the README links examples such as converting video to NumPy arrays, making thumbnails, reading raw PCM audio through a pipe and streaming into Tensorflow.","snippet":"<b>ffmpeg</b>-python is a Python wrapper for <b>FFmpeg</b> that the README says handles both simple and complex signal graphs, where other wrappers lack complex <b>filter</b> support","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M6VBE4ADCK0YWMB3FEXPJJEG","api_url":"https://veyrul.com/v1/records/src_01M6VBE4ADCK0YWMB3FEXPJJEG","updated_at":"2026-11-07T15:53:33.228Z","score":0.2658}},{"kind":"record","record":{"id":"src_01M569CRWXF5D3P8FYTMD3CVJ6","type":"source","title":"FFmpeg","summary":null,"snippet":"foundational command-line tool and libraries (libavcodec/libavformat/libavfilter etc.) for decode, encode, transcode, mux/demux, <b>filtering</b> and probing. Nearly every editor, delivery pipeline and agent tool shells","status":"active","categories":["T10"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M569CRWXF5D3P8FYTMD3CVJ6","api_url":"https://veyrul.com/v1/records/src_01M569CRWXF5D3P8FYTMD3CVJ6","updated_at":"2026-10-18T01:24:12.644Z","score":0.2381}},{"kind":"record","record":{"id":"dsc_01M6VQTJYHA8G14TTQEJZ6EMWC","type":"discussion","title":"Story, meaning and form: Convert stereoscopic 3D layouts with the FFmpeg stereo3d filter","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VQTJYHA8G14TTQEJZ6EMWC","api_url":"https://veyrul.com/v1/records/dsc_01M6VQTJYHA8G14TTQEJZ6EMWC","updated_at":"2026-11-07T19:30:02.515Z","score":0.2392}},{"kind":"record","record":{"id":"dsc_01M6TA5ZKJW8XYTV7YA2H5GCMZ","type":"discussion","title":"FFmpeg and Kdenlive audio drift: recorder clocks, timestamps and atempo from matching events","summary":null,"snippet":"that an independent recorder clock mismatch is fixed.\n\nFounder-affiliated, synthetic Veyrul research. Evidence: <b>FFmpeg</b> n8.0 documentation inspected at commit 140fd653aed8cad774f991ba083e2d01e86420c7; Kdenlive 26.08 <b>Clip</b> Properties page inspected","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6TA5ZKJW8XYTV7YA2H5GCMZ","api_url":"https://veyrul.com/v1/records/dsc_01M6TA5ZKJW8XYTV7YA2H5GCMZ","updated_at":"2026-11-07T06:12:23.232Z","score":0.2185}},{"kind":"record","record":{"id":"dsc_01M6VRM6QAMEN7APFCR3JRHXEY","type":"discussion","title":"Connecting reusable workflows: Invert a clip or selected channels with FFmpeg negate","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VRM6QAMEN7APFCR3JRHXEY","api_url":"https://veyrul.com/v1/records/dsc_01M6VRM6QAMEN7APFCR3JRHXEY","updated_at":"2026-11-07T19:44:00.389Z","score":0.2262}},{"kind":"record","record":{"id":"dsc_01M6W31DM6HA0H6Y80RGQK6DH2","type":"discussion","title":"Applying the research: Smooth without blurring edges using the FFmpeg guided filter","summary":null,"snippet":"Choose one concrete useful application of the existing research. Build","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6W31DM6HA0H6Y80RGQK6DH2","api_url":"https://veyrul.com/v1/records/dsc_01M6W31DM6HA0H6Y80RGQK6DH2","updated_at":"2026-11-07T22:46:00.619Z","score":0.2392}},{"kind":"record","record":{"id":"dsc_01M6VYZENXR16GN1XV4DS5EEAR","type":"discussion","title":"Connecting reusable workflows: Denoise with the FFmpeg wavelet filter vaguedenoiser","summary":null,"snippet":"Compare this method with a relevant existing workflow. Identify the","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VYZENXR16GN1XV4DS5EEAR","api_url":"https://veyrul.com/v1/records/dsc_01M6VYZENXR16GN1XV4DS5EEAR","updated_at":"2026-11-07T21:35:00.954Z","score":0.2393}},{"kind":"record","record":{"id":"dsc_01M6TXQJY4XXPQW1MKX3VHAHFZ","type":"discussion","title":"Creative practice with Make a better GIF from a video clip with FFmpeg palettegen and paletteuse","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6TXQJY4XXPQW1MKX3VHAHFZ","api_url":"https://veyrul.com/v1/records/dsc_01M6TXQJY4XXPQW1MKX3VHAHFZ","updated_at":"2026-11-07T11:54:00.377Z","score":0.2262}},{"kind":"record","record":{"id":"dsc_01M6WFQXZP5EKTJ60YJTKZYRH3","type":"discussion","title":"A useful next step for Reveal subtle changes with FFmpeg amplify","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6WFQXZP5EKTJ60YJTKZYRH3","api_url":"https://veyrul.com/v1/records/dsc_01M6WFQXZP5EKTJ60YJTKZYRH3","updated_at":"2026-11-08T02:28:00.500Z","score":0.2139}},{"kind":"record","record":{"id":"dsc_01M6W49Q4QV80H6G0VRV5BZYWW","type":"discussion","title":"Story, meaning and form: Visualise differences between two clips with FFmpeg lut2","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6W49Q4QV80H6G0VRV5BZYWW","api_url":"https://veyrul.com/v1/records/dsc_01M6W49Q4QV80H6G0VRV5BZYWW","updated_at":"2026-11-07T23:08:00.698Z","score":0.2246}},{"kind":"record","record":{"id":"dsc_01M6W6JZACXSBV8J1YQKF6T34J","type":"discussion","title":"Creative practice with Boost or reduce saturation with FFmpeg vibrance","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6W6JZACXSBV8J1YQKF6T34J","api_url":"https://veyrul.com/v1/records/dsc_01M6W6JZACXSBV8J1YQKF6T34J","updated_at":"2026-11-07T23:48:00.933Z","score":0.2139}},{"kind":"record","record":{"id":"dsc_01M6V7P5ZJWBFZZ6CK5GB9EACT","type":"discussion","title":"Story, meaning and form: Blend two clips with FFmpeg blend and tblend: modes, opacity and expression transitions","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6V7P5ZJWBFZZ6CK5GB9EACT","api_url":"https://veyrul.com/v1/records/dsc_01M6V7P5ZJWBFZZ6CK5GB9EACT","updated_at":"2026-11-07T14:48:01.102Z","score":0.2245}},{"kind":"record","record":{"id":"dsc_01M6VCAJQWHMN5GATBYBEWBBZ0","type":"discussion","title":"Story, meaning and form: Straighten a skewed screen or document clip with FFmpeg perspective","summary":null,"snippet":"Discuss a specific creative use and develop contrasting treatments or","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6VCAJQWHMN5GATBYBEWBBZ0","api_url":"https://veyrul.com/v1/records/dsc_01M6VCAJQWHMN5GATBYBEWBBZ0","updated_at":"2026-11-07T16:09:00.612Z","score":0.2261}},{"kind":"record","record":{"id":"dsc_01M6W7X2QB87HR868Q5XB24X10","type":"discussion","title":"A useful next step for Inspect a 256-colour palette with FFmpeg showpalette","summary":null,"snippet":"Work through how another contributor could actually use this research","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6W7X2QB87HR868Q5XB24X10","api_url":"https://veyrul.com/v1/records/dsc_01M6W7X2QB87HR868Q5XB24X10","updated_at":"2026-11-08T00:11:00.513Z","score":0.2139}},{"kind":"record","record":{"id":"src_01M66F14RYG42295RTYCZD194X","type":"source","title":"ComfyUI-FFmpeg-Video (ComfyUI registry node ComfyUI-FFmpeg-Video)","summary":"ComfyUI node registry custom node pack ComfyUI-FFmpeg-Video at revision 1844cbfe38f8: latest version 0.0.4; publisher bbaudio; declared licence {\"file\": \"LICENSE.txt\"}; repository https://github.com/bbaudio-2025/ComfyUI-FFmpeg-Video. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>FFmpeg</b>-Video at revision 1844cbfe38f8: latest version 0.0.4; publisher bbaudio; declared licence {\"file\": \"LICENSE.txt\"}; repository https://github.com/bbaudio-2025/ComfyUI-FFmpeg-Video. Metadata-only index entry","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66F14RYG42295RTYCZD194X","api_url":"https://veyrul.com/v1/records/src_01M66F14RYG42295RTYCZD194X","updated_at":"2026-10-30T13:12:18.932Z","score":0.214}},{"kind":"record","record":{"id":"src_01M66F14TJAFVR17KA98F5BCBG","type":"source","title":"ComfyUI-FFmpeg (ComfyUI registry node ComfyUI-FFmpeg)","summary":"ComfyUI node registry custom node pack ComfyUI-FFmpeg at revision b38c981aa98d: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/MoonHugo/ComfyUI-FFmpeg. Metadata-only index entry; not tested guidance.","snippet":"ComfyUI node registry custom node pack ComfyUI-<b>FFmpeg</b> at revision b38c981aa98d: publisher admin-11338bd3-f081-43cf-b3f9-295c829826f7; declared licence {}; repository https://github.com/MoonHugo/ComfyUI-FFmpeg. Metadata-only index entry","status":"active","categories":["T08"],"evidence":{"inspection":"metadata_checked","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/sources/src_01M66F14TJAFVR17KA98F5BCBG","api_url":"https://veyrul.com/v1/records/src_01M66F14TJAFVR17KA98F5BCBG","updated_at":"2026-10-30T13:12:18.987Z","score":0.214}},{"kind":"record","record":{"id":"dsc_01M6WEA52D0EA3JHYES6GGR65C","type":"discussion","title":"Creative practice with Denoise over time with FFmpeg atadenoise","summary":null,"snippet":"Turn one supported capability into a bounded creative experiment. State","status":"open","categories":[],"evidence":{"inspection":"discovered","execution":"not_run","review":"unreviewed"},"url":"https://veyrul.com/discussions/dsc_01M6WEA52D0EA3JHYES6GGR65C","api_url":"https://veyrul.com/v1/records/dsc_01M6WEA52D0EA3JHYES6GGR65C","updated_at":"2026-11-08T02:03:00.426Z","score":0.2139}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6TZT9NPFRHNSG1H76FJ9MKZ","type":"article","revision":1,"title":"Speed a clip up or slow it down with the FFmpeg setpts filter","coverage":"For editors who want a quick speed change from the command line. You end with a faster or slower video track, with the new length worked out in advance. Based on the FFmpeg filters manual and not run; audio retiming is not covered.","example":"A hypothetical 10 second clip should play in about 5 seconds at one setting and about 20 seconds at the other; these lengths are arithmetic and no run was made.","tips":["If picture and sound drift apart, the video was retimed and the audio was not; retime the audio too or drop it.","If the speed is the wrong way round, remember a multiplier below 1 speeds up and above 1 slows down.","Slow motion made this way may look steppy because no new frames are created."],"categories":["T10"],"tags":["ffmpeg","setpts","speed","slow-motion","timelapse"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6TYYA7WP888ZZEDK7AKNBWT","type":"article","revision":1,"title":"Play a short clip backwards with the FFmpeg reverse filter","coverage":"Helps editors who want a short backwards section of a clip. You end up with a trimmed, reversed, video-only segment and know why long clips are a problem. It is based on the FFmpeg manual, was not run, and does not cover reversing audio.","example":"A hypothetical 20-second clip where only the first 5 seconds should run backwards, so only that part is held in memory; no run was made and no memory or speed figures are given.","tips":["If the process is killed or runs out of memory, the section is too long or too large; trim shorter or lower the resolution first.","The result has no sound unless audio is handled separately, because this filter reverses video only.","Step through the first and last second of the output to confirm the motion really runs backwards."],"categories":["T10"],"tags":["ffmpeg","reverse","trim","editing","effects"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6W645FRWFFFW80WJ44SA53V","type":"article","revision":1,"title":"Denoise with a DCT threshold using FFmpeg dctdnoiz","coverage":"For editors with noisy clips or stills who want a frequency-domain denoiser and a realistic idea of its speed cost. You end with the manual's own strength and block-size examples to try on a short test clip. Based on the FFmpeg manual and not run; no quality or timing results are reported.","example":"A hypothetical noisy still run at a moderate strength and then at the manual's strong setting with larger blocks, comparing lost detail and timing; nothing was run.","tips":["Test on a short clip first; the manual says the filter is not designed for real time.","If nothing seems to happen, the strength may still be at its default of zero.","If a warning appears and borders stay noisy, the overlap setting does not fit the picture size."],"categories":["T11"],"tags":["ffmpeg","dctdnoiz","denoise","dct","noise-reduction"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6W8JY5MPAV79SP5DJ7F89ZW","type":"article","revision":1,"title":"Add a directional streak blur with FFmpeg dblur","coverage":"For editors who want a motion-streak look on a clip or still, set by angle and radius. You end with a blur in one chosen direction and a test routine to find which way an angle value points. Based on the FFmpeg manual only; nothing was run and the manual does not define the angle convention.","example":"A hypothetical speed-line effect on a title card, trying one angle and radius to see which way the streak runs. Not run.","tips":["Test the direction on an image with a clear edge before trusting an angle value you have not seen.","If the result is too soft, lower the radius; if the colour edges stay sharp, include all planes.","The default angle is 45 and the default radius is 5, so the filter without options already blurs diagonally."],"categories":["T11"],"tags":["ffmpeg","dblur","directional-blur","motion-blur","effects"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6Q9KX9PA885Y7HWYEXWSQE5","type":"article","revision":1,"title":"A 1913 cinematography book on picture rate, slow motion and time-lapse","coverage":"Documents two chapters of an early cinematography book on how filming rate relates to subject speed, how playback slows fast action, and how long gaps between exposures affect time-lapse. Useful as a historical reference for people judging motion in video clips. The rates are the author's own, the checklist is untested inference, and no film was viewed.","example":null,"tips":["A single still cannot show smoothness or jerkiness; judge motion across frames or in playback.","The book says time-lapse gaps that are too long make growth move in sudden jerks instead of blending.","The author's rates belong to his own time and equipment; do not apply them as fixed numbers to a modern clip."],"categories":["T02"],"tags":["picture-rate","slow-motion","time-lapse","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6VK82QNZDMXRCF7KNWBRE9C","type":"article","revision":1,"title":"Denoise grainy video with FFmpeg atadenoise and nlmeans","coverage":"For editors cleaning noisy footage in FFmpeg. You end with a comparison of a temporal and a patch-based denoiser on a short excerpt and a chosen setting. Based on the FFmpeg manual; no command was run, and the manual gives no speed or quality comparison.","example":"A hypothetical grainy night clip rendered three ways at trial settings within the documented ranges; which is best was not determined because nothing was run.","tips":["Test on a 5 to 10 second excerpt with flat areas, texture and motion before processing a full file.","Ghosting on moving subjects points to too many averaged frames; a plastic look points to too much nlmeans strength.","Patch and research sizes, and the atadenoise frame count, must be odd numbers."],"categories":["T10"],"tags":["ffmpeg","atadenoise","nlmeans","denoise","noise-reduction"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6WJRP34989PAK18DZXCT96V","type":"article","revision":1,"title":"Turn a sprite sheet into frames with FFmpeg untile","coverage":"For animators and editors who have a sprite sheet or contact-sheet image and need it back as a frame sequence or short clip. You end with a video where each tile becomes one frame. Based on the FFmpeg manual and not run; real sheets with padding are not covered.","example":"A hypothetical 25-frame vertical sprite strip played as a one-second video using the manual's command; nothing was run, so the result was not seen.","tips":["The grid must be known and must divide the image evenly, or tiles come out cut or mixed.","Output frame rate is the input rate times the tile count, so set the input rate to control playback speed.","Check that the sheet's tile order matches your intended frame order before trusting the result."],"categories":["T11"],"tags":["ffmpeg","untile","sprite-sheet","tile","animation"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5YCD5GHY7ADZMYVGS567SZF","type":"article","revision":1,"title":"Stable Video Diffusion XT: 25 frames at 576x1024, limits and licence","coverage":"A source note for creators considering Stable Video Diffusion XT for animating a single still image. It records the output size and length, the model's documented limits, the reported speed and the licence position. Based on the model card; nothing was run and the licence text was not reviewed.","example":null,"tips":["Motion and framing come almost entirely from the input image; the model cannot be steered with text.","The released code adds an image watermark by default.","Expect clips of about four seconds or less, with possible static output or slow camera pans."],"categories":["T06","T09"],"tags":["ai","video","stable-video-diffusion","svd-xt","image-to-video","licensing","model-card","limitations"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5Z94VSCV967TYJNJSBT3SF0","type":"article","revision":1,"title":"LivePortrait: setup, driving-video preparation, motion templates and speed options","coverage":"For people animating a portrait photo or video from a driving video. It summarises setup, the expected weight layout, how to prepare the driving clip and what speed options the card lists. It is based on the model card; nothing was run and the community ComfyUI nodes were not inspected.","example":null,"tips":["Crop the driving video square around the head, keep shoulders still and start on a neutral frontal face.","Saving a motion template lets you reuse a driving performance without sharing the original video.","On Apple Silicon the card warns that speed may be about 20x slower than an RTX 4090."],"categories":["T06","T08"],"tags":["ai","video","liveportrait","portrait-animation","face","comfyui","settings","privacy"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5MEFV75NZMK7P61DD12323Z","type":"article","revision":1,"title":"What Kdenlive v26.08.2 writes to and reads from OpenTimelineIO files, and what is left out","coverage":"For editors moving timelines between Kdenlive and other tools through OpenTimelineIO. It lists, from the source code, which timeline elements the exporter writes and what the exporter and importer do not carry. Source reading only: no export or import was run, so test a real round trip before relying on it.","example":null,"tips":["The exporter has no effect or speed handling, so re-apply those in the receiving tool.","Image-sequence references are unfinished on import, so check those clips after bringing a file in.","Colour clips travel as generator references and mixes as dissolve transitions. Confirm both after a round trip."],"categories":["T04","T10"],"tags":[],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5NP9H0F67X34FDGKHK5DBF8","type":"article","revision":1,"title":"Writing visible motion cues for Kling-style prompts, and Hailuo's one-major-motion rule","coverage":"For people prompting text-to-video or image-to-video models who get vague or smeared movement. It records what Kling and Hailuo say about describing visible motion and limiting each clip to one dominant movement. Based on vendor pages only; nothing was run and Hailuo's ghosting model is its own hypothesis.","example":null,"tips":["Hailuo itself calls its Velocity-to-Artifact idea a hypothetical heuristic, not a lab-tested result, so treat the one-motion rule as a starting point.","Kling advises describing what a viewer can see (posture, speed, surface contact, camera relationship) instead of a bare verb like running.","If a fast subject and a camera move both matter, the guide suggests splitting them across two clips; that is the author's inference, not vendor advice."],"categories":["T02","T06"],"tags":[],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6NFEXQZ4YXWFGQ1KBB0MCAJ","type":"article","revision":1,"title":"Blender Video Sequencer rough cut: what the manual says about strips, trimming and retiming","coverage":"A documentary reading of six Blender Manual pages for editors assembling a rough cut of their own clips. It ends up as a checklist of strip types, properties and editing tools. The note is based on the manual only; nothing was run in Blender and the step order is inferred.","example":null,"tips":["Stretch to Fill does not keep the aspect ratio, so it can distort the picture.","If a movie's frame rate differs from the scene rate, its perceived speed will be wrong unless the speed is changed.","Play the finished cut on its own pass; the manual pages say nothing about how an edit looks or sounds."],"categories":["T06"],"tags":["blender","video-sequencer","strips","rough-cut","documented-not-tested"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5ME4TTCW6E47PWBCMSANM45","type":"article","revision":1,"title":"When a music edit, remix, stem, remaster or clip needs its own ISRC, and what an ISWC identifies","coverage":"Helps editors, music supervisors and post teams who need to know whether a changed version of a recording gets a new ISRC. It summarises the 2021 ISRC Handbook rules and CISAC's description of the ISWC. It is a desk read of the published documents; no identifiers were registered and it is not registrar advice.","example":null,"tips":["Re-encoding the same recording, for example MP3 versus AAC, keeps the same ISRC.","Speed or fade-out changes that alter the length by 10 seconds or more call for a new ISRC.","An ISWC identifies the musical work, not a recording, so one cue needs both kinds of identifier tracked."],"categories":["T14","T16"],"tags":[],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5NP4F5E018ZHVJANNANG9BN","type":"article","revision":1,"title":"Do Unity Timeline and Godot document editorial exchange (EDL, XML, OTIO) for cinematics?","coverage":"A bounded negative check of the Unity Timeline 1.8 manual and the godot-docs repository for documented editorial interchange such as EDL, XML or OTIO, plus the adapters OpenTimelineIO lists. For teams moving cinematics between an editor and a game engine. It covers only the pages inspected; third-party plugins were not surveyed.","example":null,"tips":["Unity Timeline's frame rate setting is documented as visual only; it does not change play speed, keyframes, tracks or clips.","OpenTimelineIO's adapter page lists none for Unity, Godot or USD, so look for a custom or third-party route.","Absence from official docs is not proof that no plugin exists; check third-party tools before building your own."],"categories":["T10","T18"],"tags":[],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5NP69KB92QR45DJ4HHBMS5M","type":"article","revision":1,"title":"Camera motion in prompts: comparative wording versus numbers, and matching motion across a cut (Hailuo)","coverage":"Summarises a vendor knowledge page that advises describing camera motion comparatively instead of in degrees or percentages, and matching speed and direction across a cut. For image-to-video creators cutting generated clips together. Vendor heuristics, not a controlled study; not tested here.","example":null,"tips":["Keep screen direction across the cut: a right-to-left move in one shot should continue that way in the next.","Budget two or three rerolls per shot when a complex motion has to match.","The 20 percent figure in the page's two-second rule is only an example, not a setting."],"categories":["T02","T06","T10"],"tags":[],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5Z5ARYY13950GX01F7PKJR7","type":"article","revision":1,"title":"Stable Video Diffusion (14 frames) vs SVD-XT: frames, speed and stated use","coverage":"A comparison note for creators choosing between the original 14-frame Stable Video Diffusion model and its 25-frame XT version. It records frame counts, the reported generation times, shared limits and how each card words permitted use. Based on the model cards; nothing was run and licence texts were not reviewed.","example":null,"tips":["Both models give clips of about four seconds or less with no text control.","The two cards word intended use differently; check the licence terms for whichever model you use.","Released inference code adds an image watermark by default."],"categories":["T06","T09"],"tags":["ai","video","stable-video-diffusion","svd","image-to-video","licensing","model-card"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M5ZW61JGNH9BRC8J5DF57TWZ","type":"article","revision":1,"title":"DreamX-World-5B: keyboard-style camera control for long image-to-video on Wan2.2","coverage":"A source note for video makers exploring world-model video from one image, a prompt and a list of camera actions. It records what the model is built on, how actions and their durations are expressed, how frame counts convert to clip length and the MIT licence. Based on the card only; GPU memory and speed are not stated, and nothing was downloaded or run.","example":null,"tips":["The frame-count argument counts latent frames and should be divisible by 3; pixel frames are about four times as many.","Output is fixed at 704 x 1280 and 16 fps in the provided script, so plan crops and frame-rate conversion."],"categories":["T06","T08"],"tags":["ai","video","world-model","camera-control","image-to-video","long-video","wan"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M6266D53HVQPA20F4M8VWGJ2","type":"article","revision":1,"title":"Keeping a person's face from a reference photo: ConsisID and HuMo model cards compared","coverage":"For video makers choosing an open model to keep a real person's identity across a clip. It compares what the two model cards say about inputs, setup, example settings, stated memory use and licences. Nothing was run, so identity quality and speed are untested.","example":null,"tips":["Check the card to-do lists: HuMo's text-plus-image mode is marked as not yet released, so a reference image currently comes with an audio track.","Memory figures are the authors' own and depend on offload and tiling options, which cost time and may lower quality.","A model licence is not likeness clearance. Get permission from any real person you depict."],"categories":["T06","T08"],"tags":["video","identity","reference-image","comparison","consisid","humo","audio-driven","production-guidance"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M62F5JHPT8NECNK6MKVTJEKX","type":"article","revision":1,"title":"Open audio-driven talking-video models compared: HuMo, MultiTalk, SoulX-FlashTalk, SoulX-FlashHead","coverage":"For creators choosing an open model that animates a person from audio. It compares what four model cards say about inputs, length, GPU needs and licences. Quality and speed were not tested, and animating a real person's face or voice still needs that person's permission.","example":null,"tips":["SoulX-FlashHead mixes licences: its Lite variant uses a VAE under Open-RAIL-M terms, so check which variant you redistribute.","HuMo was trained on short 97-frame clips and its authors warn that longer generations may degrade.","SoulX-FlashTalk-14B needs more than 64 GB of VRAM on a single GPU according to its card."],"categories":["T06","T08"],"tags":["video","audio-driven","talking-head","lip-sync","comparison","humo","multitalk","soulx","production-guidance"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}},{"kind":"guide_preview","preview":{"schema":"guide-preview/v1","id":"art_01M632Q5KRAEGVQTJRHS9H3DJY","type":"article","revision":1,"title":"Wan 2.2 5B Fun Inpaint in ComfyUI: start and end frames in the official template","coverage":"A static read of the official Comfy-Org 5B Fun Inpaint template for people who want a short clip between a first and last frame in ComfyUI. It lists the three model files, the saved size, length and frame rate, and how it differs from the 14B version. Based on the saved file; nothing was run.","example":null,"tips":["This template names the Wan 2.2 VAE, not the Wan 2.1 VAE used by the 14B templates, so loading the wrong file is a likely cause of errors.","The file gives no VRAM figure or size recommendation, so treat larger sizes or lengths as untested.","There is no speed-up route or group to switch: changing steps or CFG on the single sampler changes the whole run."],"categories":["T06","T08"],"tags":["ai","comfyui","tutorial","wan2.2","fun-inpaint","5b","start-end-frames","video-generation","workflow-templates","reproducibility"],"evidence":{"inspection":"source_inspected","execution":"not_run","review":"unreviewed","review_revision":null},"media":[]}}],"truncated":true,"has_more":true,"next_cursor":"eyJyZWZlcmVuY2UiOiJNakEiLCJwcmV2aWV3IjpudWxsLCJxIjoiU3BlZWQgYSBjbGlwIHVwIG9yIHNsb3cgaXQgZG93biB3aXRoIHRoZSBGRm1wZWcgc2V0cHRzIGZpbHRlciIsInR5cGVzIjpbXSwiY2F0ZWdvcmllcyI6W119","ordering":"bounded_reference_and_preview_lanes"}