[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"skill:01M7B952AEQWHG7XPRRNBG6P9W":3,"skill-same:01M7B952AEQWHG7XPRRNBG6P9W":64},{"skillNo":4,"name":5,"nameZh":6,"description":7,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":6,"sourceHtmlUrl":16,"categories":17,"keywords":18,"publishedAt":19,"linkOnly":20,"markdownContent":21,"markdownBody":22,"frontMatter":23,"refName":34,"commitSha":35,"skillDirectory":36,"forksCount":37,"repositoryHtmlUrl":38,"repositoryHomepageUrl":39,"ownerHtmlUrl":40,"ownerBlogUrl":41,"ownerDescription":42,"updatedAt":43,"install":44,"resources":57},"01M7B952AEQWHG7XPRRNBG6P9W","scene-recast-video",null,"Remake a known scene with a new cast: give a video model a short reference clip (a film scene, a dance, a fight, a news shot, a meme) plus photos of your own characters and a \"replace, keep, never\" prompt, and get your version with the motion, timing, camera and cuts of the original. Covers trimming the clip, character references, the recast prompt, new dialogue, the first-frame lock, the motion-only plate (greyscale or depth), three varg routes (Seedance 2.5 with a video reference, MiniMax H3 Max Recast, Wan 3), a frame-by-frame check against the source and a stacked original-vs-remake export. Use when someone wants a parody of a movie scene, \"this scene but with X\", a character swap, a motion-control remake, a live-action version of a game or anime scene, a meme recast, or asks how the Higgsfield Genjutsu \u002F Seedance video-reference remakes on X are made. For the joke, format choice and the rules for real people use ai-parody-video; for a talking monologue use multi-angle-monologue.","hashgraph-online\u002Fawesome-codex-plugins","hashgraph-online","https:\u002F\u002Favatars.githubusercontent.com\u002Fu\u002F160371962?v=4","01M6CNB6NRJVNNGN14TR01Q6D3","HOL (Hashgraph Online)","01M6JT1HSKKG9V68KQAQGBA7XP",1575,"MIT","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fscene-recast-video\u002FSKILL.md",[],[],"2026-11-15 14:19:17",false,"---\nname: scene-recast-video\ndescription: >-\n  Remake a known scene with a new cast: give a video model a short reference clip (a film scene,\n  a dance, a fight, a news shot, a meme) plus photos of your own characters and a \"replace, keep,\n  never\" prompt, and get your version with the motion, timing, camera and cuts of the original.\n  Covers trimming the clip, character references, the recast prompt, new dialogue, the\n  first-frame lock, the motion-only plate (greyscale or depth), three varg routes (Seedance 2.5\n  with a video reference, MiniMax H3 Max Recast, Wan 3), a frame-by-frame check against the\n  source and a stacked original-vs-remake export. Use when someone wants a parody of a movie\n  scene, \"this scene but with X\", a character swap, a motion-control remake, a live-action\n  version of a game or anime scene, a meme recast, or asks how the Higgsfield Genjutsu \u002F Seedance\n  video-reference remakes on X are made. For the joke, format choice and the rules for real\n  people use ai-parody-video; for a talking monologue use multi-angle-monologue.\nlicense: MIT\nmetadata:\n  author: vargHQ\n  version: \"1.0.0\"\n  openclaw:\n    requires:\n      anyBins:\n        - curl\n    homepage: https:\u002F\u002Fvarg.ai\u002Fhow-to\ncompatibility: >-\n  Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection\n  (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). ffmpeg and ffprobe to trim, compare and stack.\nallowed-tools: Bash(curl:*) Bash(jq:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit\n---\n\n# Scene recast: a reference clip, your cast, the same motion\n\nA video model with a video reference copies what is hard to write in a prompt (blocking, timing, camera, cuts) and takes who and what is on screen from your images. Creators call it motion control or a remake. The method below is read from the public posts of [@Arminn_Ai](https:\u002F\u002Fx.com\u002FArminn_Ai) (X, September to November 2026), who describes it as: \"You give it a reference clip plus your own character references and a prompt, and it generates your version while keeping the motion, timing and framing of the original\" and \"just the source video + refs + prompt. A 30 s render takes about 5 min. Easier shots can land in one try, harder ones usually need a few prompt passes.\" His tool is Higgsfield Genjutsu, which he says runs on Seedance 2.5; the same inputs work on varg.\n\nGeneration runs on varg: REST `https:\u002F\u002Fapi.varg.ai\u002Fv2` (the `varg-ai` skill) or the MCP server `https:\u002F\u002Fmcp.varg.ai\u002Fmcp`. Price every run first (`POST \u002Fv2\u002Festimate` or `estimate_cost`).\n\n## 1. Ask, then go\n\n- **The clip:** a link or a file, and which 5 to 30 seconds. No clip yet: `find-movie-clips` (clip databases, download, the scene split into uncut takes). A link: `media-download`.\n- **The new cast:** one to four characters, each as a photo or a sheet (`varg-character-design`, `character-passport`). Who replaces whom, by position: \"the man on the left in the black coat\".\n- **What else changes:** props, the room, the era, the dialogue. Everything not named stays.\n- **Where it goes:** aspect ratio, and whether to post it stacked over the original (section 7).\n- **Whose face and whose footage:** read \"Before you start\" in `ai-parody-video`. A real person in the cast needs their consent or a clear, labelled parody of a public figure; a provider block is a no, not a puzzle.\n\n## 2. Prepare the clip\n\n```bash\nffprobe -v error -show_entries format=duration -of csv=p=0 scene.mp4\n# cuts: every shot must be 15 s or shorter for Recast, and a run holds about 3 to 6 cuts well\nffmpeg -i scene.mp4 -vf \"select='gt(scene,0.3)',showinfo\" -an -f null - 2>&1 | grep -o 'pts_time:[0-9.]*'\n# trim on a cut, 24 fps, 720p, no audio (new dialogue comes from the model or from the edit)\nffmpeg -ss 12.0 -to 27.0 -i scene.mp4 -an -r 24 -vf \"scale=-2:720\" -c:v libx264 -crf 18 plate.mp4\n```\n\n- Keep one place per run. A change of location is a new run, joined in the edit.\n- Remove burned-in subtitles and logos by cropping (`crop=iw:ih*0.86:0:0`); text in the plate comes back as garbled text.\n- More than 30 seconds: split on cuts into runs of 10 to 30 s and carry the same references into each.\n\n## 3. References: one image per thing that changes\n\n- A character needs a face that fills at least a third of the image, the outfit visible, even light. Two angles beat one. Images narrower than 300 px are rejected on the byteplus route.\n- Match the pose family of the plate. A seated plate with a full-body standing reference drifts less than the other way round, but a reference in a wildly different costume fights the plate.\n- If the outfit should come from the plate (\"same black leather coat, new face\"), say so in the prompt and crop the reference to head and shoulders.\n- A prop or vehicle: three-quarter front and rear views on a plain background.\n\n## 4. The recast prompt: replace, keep, never\n\nShort when the clip carries the direction. The structure Armin posts for his remakes, with the slots opened up:\n\n```\nReplace \u003Cwho or what in @video1, by position and clothing> with the exact \u003Cperson\u002Fobject> from\n@image1. Copy it exactly as shown: \u003Cface, hair, glasses, build, outfit \u002F make, model, colour,\ndetails>. Do not change, redesign or swap it for anyone else.\nReplace \u003Csecond target> with the exact \u003Cperson> from @image2: \u003Cdetails>.\nKeep the original environment, \u003Cnamed set pieces>, lighting, camera movement, framing, timing\nand scene progression from @video1. Everyone else stays as they are.\n\u003CDialogue, in order: who says it, the line in quotes, the tone.>\n\u003COne line for the new event, if any: \"At the end, the man at the fountain turns and is \u003C...>\">\nPhotorealistic, cinematic, natural motion. No extra cuts, no camera jumps, no distortion, no\nwarped faces, no changing outfit, no different person, no subtitles, captions, watermarks or\ntext, no extra objects, no AI artifacts.\n```\n\n- Name targets by where they stand and what they wear. A position is what the model can see in the plate; a name tells it nothing about which figure you mean.\n- Changes at set times: \"Preserve the source motion, camera and timing throughout. Apply the following changes by timecode: 0.0–3.0 s Environment: \u003C...>. Main character: \u003C...>.\" Object swaps \"matching position, angle and movement frame for frame\". State when a look ends: \"The anime look ends completely at 17.0 s and does not carry over.\"\n- Dialogue changes the mouths. If the original speaks and you want other words, write the new lines; if you want silence under music, say \"nobody speaks\".\n- One new event per run (the turn, the reveal). Two and the model drops the plate's timing.\n\n## 5. Three routes on varg\n\n| Route | Send | Use it when |\n|---|---|---|\n| MiniMax H3 Max Recast, `minimax_h3_max_recast` | `files`: the video (5 to 30 s, no shot over 15 s), then up to four photos; optional `prompt` (\"the man becomes the wizard from the photo\"); `provider_options.fal.enhance_realism: true` | Start here. Only the people change: room, props, camera and every move stay. Output at 768p or 1080p. |\n| Seedance 2.5 with a video reference, `seedance_2_5` | `files`: the plate, then the images (`@video1`, `@image1…`), up to 3 videos and 9 images, 4 to 30 s, `provider_options.piapi.input.omni_reference_task_type: \"reference\"` | When more than the people should change (set, style, an added event), or you want native audio. The scene is redrawn from the plate, so small set details shift. |\n| Wan 3, `fal:alibaba\u002Fwan-3.0\u002Freference-to-video` | reference videos (up to 5), images (up to 10), audio (up to 5), 2 to 30 s, 1080p | A second opinion, or when you also bring a voice clip. Not tested here. |\n\n```bash\n# Recast: the plate and one character sheet\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"minimax_h3_max_recast\",\n  \"prompt\": \"the man becomes the old wizard from the reference photo\",\n  \"files\": [{\"url\":\"PLATE_MP4\"},{\"url\":\"CHARACTER_SHEET\"}],\n  \"resolution\": \"720p\"}'\n\n# Seedance 2.5: the plate as a motion reference\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"seedance_2_5\",\n  \"prompt\": \"Reference @video1 for the motion, camera movement and framing. \u003CCharacter> from @image1 performs exactly the same \u003Caction> as the man in @video1, same timing, in the same \u003Croom>. One continuous handheld take, no cuts.\",\n  \"files\": [{\"url\":\"PLATE_MP4\"},{\"url\":\"CHARACTER_SHEET\"}],\n  \"aspect_ratio\": \"9:16\", \"resolution\": \"480p\", \"duration\": 10, \"audio\": false,\n  \"provider_options\": {\"piapi\": {\"input\": {\"omni_reference_task_type\": \"reference\"}}}}'\n```\n\n### What a real run showed (varg, 2026-11-12)\n\nOne plate (a 10 s stock clip of a man dancing in a kitchen, one take, 720x1280), one character sheet (an invented wizard: face close-up plus three full-body views on grey), one run on each route, no retries:\n\n| | Recast | Seedance 2.5, reference task |\n|---|---|---|\n| Result | Same moves second by second, same kitchen down to the posters, face and costume from the sheet | Same moves second by second, face and costume from the sheet, kitchen redrawn close to the plate |\n| Output | 768x1344, 10 s, no audio (the plate had none) | 480x854, 10 s |\n| Cost | $3.00 | $2.48 at 480p |\n\nWhat failed on the way, so you do not pay to learn it:\n\n- **Seedance edit task** (`omni_reference_task_type: \"edit\"`) rejects the job unless `aspect_ratio` is `\"adaptive\"` and `duration` is `-1`. The varg body does not accept a top-level `duration` below 1, so leave it out and put both inside `provider_options.piapi.input`.\n- **The pinned standard route** (`piapi:seedance-2.5`) answered \"Content moderation violation\" three times: for the stock clip in edit and in reference mode, and for a clip of an AI-made character. It refuses a photoreal person in the reference video, licensed or generated. The `seedance_2_5` alias routes the same request to a tier that accepts it.\n- **A 480p plate** (832x480) came back \"Invalid input\"; the same clip at 1280x720 was accepted. Keep plates at 720p or more.\n- `estimate_cost` gives the ceiling: Recast showed $9.00 and charged $3.00.\n\nDraft on Seedance at 480p, check (section 6), then rerun the keeper at 720p or 1080p with the same inputs. Model facts and limits: `varg-previz\u002Freferences\u002Fseedance-v2v.md`. Armin's own comparison of the two engines he uses: the Seedance tool \"is more accurate on motion control and timing\", the MiniMax one \"drops the timing on some frames\" and \"wins on cost\"; Seedance \"goes up to 30 seconds in one clip\". On the single-take test above the two were level on timing.\n\n## 6. Check against the source, then fix\n\n```bash\n# same second from both, side by side, one row per 2 s\nffmpeg -i plate.mp4 -i take.mp4 -filter_complex \\\n \"[0:v]fps=1\u002F2,scale=480:-2[a];[1:v]fps=1\u002F2,scale=480:-2[b];[a][b]hstack,tile=1x8\" -frames:v 1 check.jpg\n```\n\n| What you see | Fix |\n|---|---|\n| The new character looks like the original actor | The reference is too small or too far from the plate's angle. Add a second angle; describe face, hair and glasses in the prompt; crop the reference tighter. |\n| The plate's costume or colours leak in | Use a motion-only plate: greyscale (`ffmpeg -i plate.mp4 -vf hue=s=0 plate_grey.mp4`) or a depth pass, and say \"@video1 is a motion plate. Use it for pose, timing, lips, hands, camera and framing. Do not copy its colour or its look. All colour comes from @image1.\" |\n| Detail degrades as the clip moves away from frame 1 | First-frame lock: edit frame 1 of the plate on an image model into your version (new cast in place, same composition), send it as `@image1` with the plate, and write \"@image1 is the first frame\". Armin: with one locked frame \"unwanted details start popping up\" later in the clip; several locked frames act \"as a proper motion control between them\", at some risk to colour consistency. |\n| Cuts land late or a shot is missing | Fewer cuts per run (split the plate), and write \"N shots, hard cuts exactly as in @video1\". |\n| The job is refused | Read the reason. Known footage or a known face: the provider has said no to this input. Change the idea (an original scene shot in the style, your own lookalike character, a different clip), do not hunt for a setting that slips it through. |\n| A hand, a prop or the crowd breaks in one stretch | Rerun, or keep the take and cut around those seconds. |\n\nA depth or greyscale plate carries movement and drops the source's look. Creators on X also use it to get known scenes past a provider's copyright check; that is bypassing moderation, which providers' terms forbid, and it is not what this skill uses the plate for.\n\n## 7. Finish\n\n- **Stacked comparison** (original on top, remake below), the format that carries \"I tested this scene\" posts:\n\n```bash\nffmpeg -i plate.mp4 -i take.mp4 -filter_complex \\\n \"[0:v]scale=1440:-2[a];[1:v]scale=1440:-2[b];[a][b]vstack\" -c:v libx264 -crf 17 -an stacked.mp4\n```\n\n- **Sound:** keep the model's dialogue if it is clean; otherwise voice and lip sync per shot (`multi-angle-monologue`, `video-sound`). Music and effects last.\n- **Subtitles:** two lines at most, lower third, white with a soft shadow (`caption-styles`). They carry the joke with the sound off.\n- **Sharper output:** `topaz_video` on the final cut, once.\n- **Label and post:** mark it as AI-made on the platform, and say it is a parody in the caption. Details in `ai-parody-video`.\n\n## Cost of a 30-second recast (estimate before you spend)\n\n| Step | Runs | About |\n|---|---|---|\n| MiniMax H3 Max Recast, 3 plates of 10 s, 2 passes each | 6 | $18 (measured: $3.00 for 10 s at 768p) |\n| Or 480p drafts on Seedance 2.5, 3 plates of 10 s, 2 passes each | 6 | $15 (measured: $2.48 for 10 s at 480p) |\n| Seedance keepers at 720p or 1080p | 3 | check `estimate_cost` |\n| Upscale | 1 | from $0.50 |\n\n## Related skills\n\n`ai-parody-video` (the joke, the format, the rules), `multi-angle-monologue`, `media-download`, `varg-character-design`, `character-passport`, `varg-previz` (your own blockout as the plate), `video-animate`, `caption-styles`, `video-sound`, `media-judge`, `varg-ai`.\n","# Scene recast: a reference clip, your cast, the same motion\n\nA video model with a video reference copies what is hard to write in a prompt (blocking, timing, camera, cuts) and takes who and what is on screen from your images. Creators call it motion control or a remake. The method below is read from the public posts of [@Arminn_Ai](https:\u002F\u002Fx.com\u002FArminn_Ai) (X, September to November 2026), who describes it as: \"You give it a reference clip plus your own character references and a prompt, and it generates your version while keeping the motion, timing and framing of the original\" and \"just the source video + refs + prompt. A 30 s render takes about 5 min. Easier shots can land in one try, harder ones usually need a few prompt passes.\" His tool is Higgsfield Genjutsu, which he says runs on Seedance 2.5; the same inputs work on varg.\n\nGeneration runs on varg: REST `https:\u002F\u002Fapi.varg.ai\u002Fv2` (the `varg-ai` skill) or the MCP server `https:\u002F\u002Fmcp.varg.ai\u002Fmcp`. Price every run first (`POST \u002Fv2\u002Festimate` or `estimate_cost`).\n\n## 1. Ask, then go\n\n- **The clip:** a link or a file, and which 5 to 30 seconds. No clip yet: `find-movie-clips` (clip databases, download, the scene split into uncut takes). A link: `media-download`.\n- **The new cast:** one to four characters, each as a photo or a sheet (`varg-character-design`, `character-passport`). Who replaces whom, by position: \"the man on the left in the black coat\".\n- **What else changes:** props, the room, the era, the dialogue. Everything not named stays.\n- **Where it goes:** aspect ratio, and whether to post it stacked over the original (section 7).\n- **Whose face and whose footage:** read \"Before you start\" in `ai-parody-video`. A real person in the cast needs their consent or a clear, labelled parody of a public figure; a provider block is a no, not a puzzle.\n\n## 2. Prepare the clip\n\n```bash\nffprobe -v error -show_entries format=duration -of csv=p=0 scene.mp4\n# cuts: every shot must be 15 s or shorter for Recast, and a run holds about 3 to 6 cuts well\nffmpeg -i scene.mp4 -vf \"select='gt(scene,0.3)',showinfo\" -an -f null - 2>&1 | grep -o 'pts_time:[0-9.]*'\n# trim on a cut, 24 fps, 720p, no audio (new dialogue comes from the model or from the edit)\nffmpeg -ss 12.0 -to 27.0 -i scene.mp4 -an -r 24 -vf \"scale=-2:720\" -c:v libx264 -crf 18 plate.mp4\n```\n\n- Keep one place per run. A change of location is a new run, joined in the edit.\n- Remove burned-in subtitles and logos by cropping (`crop=iw:ih*0.86:0:0`); text in the plate comes back as garbled text.\n- More than 30 seconds: split on cuts into runs of 10 to 30 s and carry the same references into each.\n\n## 3. References: one image per thing that changes\n\n- A character needs a face that fills at least a third of the image, the outfit visible, even light. Two angles beat one. Images narrower than 300 px are rejected on the byteplus route.\n- Match the pose family of the plate. A seated plate with a full-body standing reference drifts less than the other way round, but a reference in a wildly different costume fights the plate.\n- If the outfit should come from the plate (\"same black leather coat, new face\"), say so in the prompt and crop the reference to head and shoulders.\n- A prop or vehicle: three-quarter front and rear views on a plain background.\n\n## 4. The recast prompt: replace, keep, never\n\nShort when the clip carries the direction. The structure Armin posts for his remakes, with the slots opened up:\n\n```\nReplace \u003Cwho or what in @video1, by position and clothing> with the exact \u003Cperson\u002Fobject> from\n@image1. Copy it exactly as shown: \u003Cface, hair, glasses, build, outfit \u002F make, model, colour,\ndetails>. Do not change, redesign or swap it for anyone else.\nReplace \u003Csecond target> with the exact \u003Cperson> from @image2: \u003Cdetails>.\nKeep the original environment, \u003Cnamed set pieces>, lighting, camera movement, framing, timing\nand scene progression from @video1. Everyone else stays as they are.\n\u003CDialogue, in order: who says it, the line in quotes, the tone.>\n\u003COne line for the new event, if any: \"At the end, the man at the fountain turns and is \u003C...>\">\nPhotorealistic, cinematic, natural motion. No extra cuts, no camera jumps, no distortion, no\nwarped faces, no changing outfit, no different person, no subtitles, captions, watermarks or\ntext, no extra objects, no AI artifacts.\n```\n\n- Name targets by where they stand and what they wear. A position is what the model can see in the plate; a name tells it nothing about which figure you mean.\n- Changes at set times: \"Preserve the source motion, camera and timing throughout. Apply the following changes by timecode: 0.0–3.0 s Environment: \u003C...>. Main character: \u003C...>.\" Object swaps \"matching position, angle and movement frame for frame\". State when a look ends: \"The anime look ends completely at 17.0 s and does not carry over.\"\n- Dialogue changes the mouths. If the original speaks and you want other words, write the new lines; if you want silence under music, say \"nobody speaks\".\n- One new event per run (the turn, the reveal). Two and the model drops the plate's timing.\n\n## 5. Three routes on varg\n\n| Route | Send | Use it when |\n|---|---|---|\n| MiniMax H3 Max Recast, `minimax_h3_max_recast` | `files`: the video (5 to 30 s, no shot over 15 s), then up to four photos; optional `prompt` (\"the man becomes the wizard from the photo\"); `provider_options.fal.enhance_realism: true` | Start here. Only the people change: room, props, camera and every move stay. Output at 768p or 1080p. |\n| Seedance 2.5 with a video reference, `seedance_2_5` | `files`: the plate, then the images (`@video1`, `@image1…`), up to 3 videos and 9 images, 4 to 30 s, `provider_options.piapi.input.omni_reference_task_type: \"reference\"` | When more than the people should change (set, style, an added event), or you want native audio. The scene is redrawn from the plate, so small set details shift. |\n| Wan 3, `fal:alibaba\u002Fwan-3.0\u002Freference-to-video` | reference videos (up to 5), images (up to 10), audio (up to 5), 2 to 30 s, 1080p | A second opinion, or when you also bring a voice clip. Not tested here. |\n\n```bash\n# Recast: the plate and one character sheet\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"minimax_h3_max_recast\",\n  \"prompt\": \"the man becomes the old wizard from the reference photo\",\n  \"files\": [{\"url\":\"PLATE_MP4\"},{\"url\":\"CHARACTER_SHEET\"}],\n  \"resolution\": \"720p\"}'\n\n# Seedance 2.5: the plate as a motion reference\ncurl -s -X POST https:\u002F\u002Fapi.varg.ai\u002Fv2\u002Ftools\u002Fvideo\u002Fcall -H \"Authorization: Bearer $VARG_API_KEY\" \\\n  -H \"Content-Type: application\u002Fjson\" -d '{\n  \"model\": \"seedance_2_5\",\n  \"prompt\": \"Reference @video1 for the motion, camera movement and framing. \u003CCharacter> from @image1 performs exactly the same \u003Caction> as the man in @video1, same timing, in the same \u003Croom>. One continuous handheld take, no cuts.\",\n  \"files\": [{\"url\":\"PLATE_MP4\"},{\"url\":\"CHARACTER_SHEET\"}],\n  \"aspect_ratio\": \"9:16\", \"resolution\": \"480p\", \"duration\": 10, \"audio\": false,\n  \"provider_options\": {\"piapi\": {\"input\": {\"omni_reference_task_type\": \"reference\"}}}}'\n```\n\n### What a real run showed (varg, 2026-11-12)\n\nOne plate (a 10 s stock clip of a man dancing in a kitchen, one take, 720x1280), one character sheet (an invented wizard: face close-up plus three full-body views on grey), one run on each route, no retries:\n\n| | Recast | Seedance 2.5, reference task |\n|---|---|---|\n| Result | Same moves second by second, same kitchen down to the posters, face and costume from the sheet | Same moves second by second, face and costume from the sheet, kitchen redrawn close to the plate |\n| Output | 768x1344, 10 s, no audio (the plate had none) | 480x854, 10 s |\n| Cost | $3.00 | $2.48 at 480p |\n\nWhat failed on the way, so you do not pay to learn it:\n\n- **Seedance edit task** (`omni_reference_task_type: \"edit\"`) rejects the job unless `aspect_ratio` is `\"adaptive\"` and `duration` is `-1`. The varg body does not accept a top-level `duration` below 1, so leave it out and put both inside `provider_options.piapi.input`.\n- **The pinned standard route** (`piapi:seedance-2.5`) answered \"Content moderation violation\" three times: for the stock clip in edit and in reference mode, and for a clip of an AI-made character. It refuses a photoreal person in the reference video, licensed or generated. The `seedance_2_5` alias routes the same request to a tier that accepts it.\n- **A 480p plate** (832x480) came back \"Invalid input\"; the same clip at 1280x720 was accepted. Keep plates at 720p or more.\n- `estimate_cost` gives the ceiling: Recast showed $9.00 and charged $3.00.\n\nDraft on Seedance at 480p, check (section 6), then rerun the keeper at 720p or 1080p with the same inputs. Model facts and limits: `varg-previz\u002Freferences\u002Fseedance-v2v.md`. Armin's own comparison of the two engines he uses: the Seedance tool \"is more accurate on motion control and timing\", the MiniMax one \"drops the timing on some frames\" and \"wins on cost\"; Seedance \"goes up to 30 seconds in one clip\". On the single-take test above the two were level on timing.\n\n## 6. Check against the source, then fix\n\n```bash\n# same second from both, side by side, one row per 2 s\nffmpeg -i plate.mp4 -i take.mp4 -filter_complex \\\n \"[0:v]fps=1\u002F2,scale=480:-2[a];[1:v]fps=1\u002F2,scale=480:-2[b];[a][b]hstack,tile=1x8\" -frames:v 1 check.jpg\n```\n\n| What you see | Fix |\n|---|---|\n| The new character looks like the original actor | The reference is too small or too far from the plate's angle. Add a second angle; describe face, hair and glasses in the prompt; crop the reference tighter. |\n| The plate's costume or colours leak in | Use a motion-only plate: greyscale (`ffmpeg -i plate.mp4 -vf hue=s=0 plate_grey.mp4`) or a depth pass, and say \"@video1 is a motion plate. Use it for pose, timing, lips, hands, camera and framing. Do not copy its colour or its look. All colour comes from @image1.\" |\n| Detail degrades as the clip moves away from frame 1 | First-frame lock: edit frame 1 of the plate on an image model into your version (new cast in place, same composition), send it as `@image1` with the plate, and write \"@image1 is the first frame\". Armin: with one locked frame \"unwanted details start popping up\" later in the clip; several locked frames act \"as a proper motion control between them\", at some risk to colour consistency. |\n| Cuts land late or a shot is missing | Fewer cuts per run (split the plate), and write \"N shots, hard cuts exactly as in @video1\". |\n| The job is refused | Read the reason. Known footage or a known face: the provider has said no to this input. Change the idea (an original scene shot in the style, your own lookalike character, a different clip), do not hunt for a setting that slips it through. |\n| A hand, a prop or the crowd breaks in one stretch | Rerun, or keep the take and cut around those seconds. |\n\nA depth or greyscale plate carries movement and drops the source's look. Creators on X also use it to get known scenes past a provider's copyright check; that is bypassing moderation, which providers' terms forbid, and it is not what this skill uses the plate for.\n\n## 7. Finish\n\n- **Stacked comparison** (original on top, remake below), the format that carries \"I tested this scene\" posts:\n\n```bash\nffmpeg -i plate.mp4 -i take.mp4 -filter_complex \\\n \"[0:v]scale=1440:-2[a];[1:v]scale=1440:-2[b];[a][b]vstack\" -c:v libx264 -crf 17 -an stacked.mp4\n```\n\n- **Sound:** keep the model's dialogue if it is clean; otherwise voice and lip sync per shot (`multi-angle-monologue`, `video-sound`). Music and effects last.\n- **Subtitles:** two lines at most, lower third, white with a soft shadow (`caption-styles`). They carry the joke with the sound off.\n- **Sharper output:** `topaz_video` on the final cut, once.\n- **Label and post:** mark it as AI-made on the platform, and say it is a parody in the caption. Details in `ai-parody-video`.\n\n## Cost of a 30-second recast (estimate before you spend)\n\n| Step | Runs | About |\n|---|---|---|\n| MiniMax H3 Max Recast, 3 plates of 10 s, 2 passes each | 6 | $18 (measured: $3.00 for 10 s at 768p) |\n| Or 480p drafts on Seedance 2.5, 3 plates of 10 s, 2 passes each | 6 | $15 (measured: $2.48 for 10 s at 480p) |\n| Seedance keepers at 720p or 1080p | 3 | check `estimate_cost` |\n| Upscale | 1 | from $0.50 |\n\n## Related skills\n\n`ai-parody-video` (the joke, the format, the rules), `multi-angle-monologue`, `media-download`, `varg-character-design`, `character-passport`, `varg-previz` (your own blockout as the plate), `video-animate`, `caption-styles`, `video-sound`, `media-judge`, `varg-ai`.\n",{"name":5,"license":15,"metadata":24,"description":7,"allowed-tools":32,"compatibility":33},{"author":25,"version":26,"openclaw":27},"vargHQ","1.0.0",{"homepage":28,"requires":29},"https:\u002F\u002Fvarg.ai\u002Fhow-to",{"anyBins":30},[31],"curl","Bash(curl:*) Bash(jq:*) Bash(ffmpeg:*) Bash(ffprobe:*) Read Write Edit","Needs a VARG_API_KEY with curl (see the varg-ai skill) or the varg MCP connection (https:\u002F\u002Fmcp.varg.ai\u002Fmcp). ffmpeg and ffprobe to trim, compare and stack.","main","70b6a3a3a7c774671e45af646306e1448baf0511","plugins\u002FvargHQ\u002Fskills\u002Fscene-recast-video",491,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins","https:\u002F\u002Fhol.org\u002Fplugins\u002Fbest-codex-plugins","https:\u002F\u002Fgithub.com\u002Fhashgraph-online","https:\u002F\u002Fhol.org","Open-source standards and developer tools for interoperable AI agents: discovery, identity, communication, payments, privacy and security.","2026-11-14 14:06:13",{"source":8,"skillName":5,"commands":45,"prompt":55,"zipAvailable":56},[46,49,52],{"tool":47,"command":48},"npx","npx skills add hashgraph-online\u002Fawesome-codex-plugins --skill scene-recast-video",{"tool":50,"command":51},"bunx","bunx skills add hashgraph-online\u002Fawesome-codex-plugins --skill scene-recast-video",{"tool":53,"command":54},"pnpm","pnpm dlx skills add hashgraph-online\u002Fawesome-codex-plugins --skill scene-recast-video","安装技能，技能地址：https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fscene-recast-video\u002FSKILL.md",true,[58],{"path":59,"resourceType":60,"resourceTypeDesc":61,"sizeBytes":62,"sourceHtmlUrl":63},"README.md","REFERENCE","参考文档",6617,"https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002FvargHQ\u002Fskills\u002Fscene-recast-video\u002FREADME.md",[65,73,81,89,97,105],{"skillNo":66,"name":67,"nameZh":6,"description":68,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":69,"sourceHtmlUrl":70,"categories":71,"keywords":72,"publishedAt":19},"01M7DV332YQMGD8WTRJ9DZQXTB","worktable-review-with-annotations","Create, inspect, reply to, update, or resolve situated Worktable annotations. Use when feedback belongs to a Doc section, block, text range, or HTML Doc, or when the user asks to address existing review feedback and coordinate a requested artifact edit.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-review-with-annotations\u002FSKILL.md",[],[],{"skillNo":74,"name":75,"nameZh":6,"description":76,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":77,"sourceHtmlUrl":78,"categories":79,"keywords":80,"publishedAt":19},"01M7DV2YGHCZVBEB1AHYB6CGHE","worktable-find-and-synthesize-context","Find, assess, and synthesize context from Worktable Docs and Records. Use when the user asks what a workspace contains, wants workspace-backed research, needs current facts reconciled across artifacts, or requests a cited synthesis without changing workspace state.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-find-and-synthesize-context\u002FSKILL.md",[],[],{"skillNo":82,"name":83,"nameZh":6,"description":84,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":85,"sourceHtmlUrl":86,"categories":87,"keywords":88,"publishedAt":19},"01M7DV2TQN1H11ME2SAF9MXN7V","worktable-create-or-update-docs","Create, edit, rename, or maintain narrative Worktable Docs. Use for plans, decisions, briefs, notes, research syntheses, and other durable prose when the user requests a new artifact or a safe update to an existing one.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-update-docs\u002FSKILL.md",[],[],{"skillNo":90,"name":91,"nameZh":6,"description":92,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":93,"sourceHtmlUrl":94,"categories":95,"keywords":96,"publishedAt":19},"01M7DV2NE452NEA8TXATKSNAJH","worktable-create-or-manage-records","Organize repeated structured information as durable Worktable Records. Use for research datasets, inventories, directories, pipelines, trackers, and other collections whose items need identity, fields, filtering, links, validation, or individual updates.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-records\u002FSKILL.md",[],[],{"skillNo":98,"name":99,"nameZh":6,"description":100,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":101,"sourceHtmlUrl":102,"categories":103,"keywords":104,"publishedAt":19},"01M7DV2HENRBR2KSCVM064WH0Y","worktable-create-or-manage-interactive-html","Create or improve durable visual and interactive artifacts in Worktable. Use for dashboards, trackers, calculators, mini apps, slide presentations, and other requests that benefit from a polished HTML Doc.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-create-or-manage-interactive-html\u002FSKILL.md",[],[],{"skillNo":106,"name":107,"nameZh":6,"description":108,"descriptionZh":6,"repositoryFullName":8,"ownerLogin":9,"ownerAvatarUrl":10,"ownerAccountNo":11,"ownerDisplayName":12,"repositoryNo":13,"starsCount":14,"licenseSpdxId":15,"licenseFileUrl":109,"sourceHtmlUrl":110,"categories":111,"keywords":112,"publishedAt":19},"01M7DV2CADR5R7RQFFYPNAGR9Y","worktable-collaborate-threads","Read, answer, and hand off messages through durable Worktable threads with users or other authenticated participants. Use when the user asks to check addressed messages, reply to a participant, continue a thread, request another agent's help, wait briefly for a response, or watch for comments and messages sent to the agent.","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FLICENSE","https:\u002F\u002Fgithub.com\u002Fhashgraph-online\u002Fawesome-codex-plugins\u002Fblob\u002Fmain\u002Fplugins\u002Fworktable\u002Fworktable-plugin\u002Fskills\u002Fworktable-collaborate-threads\u002FSKILL.md",[],[]]