Update to Picsart
Snapshot Nov 3, 2026 · 18:14 UTC · version 2.3.0
Collection source: downloaded plugin package.
Instructions updated for photo-slideshow
Skill instructions — Now says: - **All seams the same?** `scene://montage` (`picsart_scene_capabilities`, section `template:scene://montage`) binds a clip list
Observed in instructions or declared skills. Runtime behavior has not been tested.
Up to 3 plugins free · no card required.
All fields and original values.
Skill instructions
Oct 27, 2026 · 06:06 UTC
- **All seams the same?** `mpscene://montage` (`picsart_scene_capabilities`, section `template:mpscene://montage`) binds a clip list
Nov 3, 2026 · 18:14 UTC
- **All seams the same?** `scene://montage` (`picsart_scene_capabilities`, section `template:scene://montage`) binds a clip list
Compare saved observations
Download comparison JSONSKILL.md text changes
− removed · + added
--- before +++ after @@ -66,7 +66,7 @@ calm transition, `crossfade`, as the default, and spend a directional one (`slide`) on the seam that should read as "next". The rendered example's `slide` `direction: "left"` visibly moves through its window. -- **All seams the same?** `mpscene://montage` (`picsart_scene_capabilities`, section `template:mpscene://montage`) binds a clip list +- **All seams the same?** `scene://montage` (`picsart_scene_capabilities`, section `template:scene://montage`) binds a clip list plus one `transition` id and `transitionDuration` for every seam. Author the track by hand as above when seams differ or a transition takes params.
Full technical diff · 1 changed fields
changed /skill_md_contents
"---\nname: photo-slideshow\ndescription: Build a photo promo or slideshow in a scene — probe the photos, sequence them as a track of clips with transitions, fill off-aspect photos with a blurred copy, add an animated title that stays readable over any photo, choose a font, and verify with a sweep of full-resolution frames. Use when asked for a photo slideshow, photo montage, photo reel, promo video from photos, Reels/Shorts/TikTok from pictures, or a titled sequence of images.\nmetadata:\n category: authoring\n version: '1'\n---\n\n# Photo promo / slideshow\n\nAssumes the font asset from picsart_scene_fonts (a `live.fonts` entry), and that picsart_scene_patch returns the patched scene you pass to the next tool.\n\nThe most common scene job: N photos, one after another, a transition at each seam, a title.\nEvery value below was validated and rendered at 1080x1920; the whole scene is in\n[the worked example](references/worked-example.md).\n\nRelated recipes: `picsart_scene_recipe scene-video-edits` owns the track, transition-window and\n`blur_fill` detail; `picsart_scene_recipe motion-intent` chooses durations and easing.\n\n## 1. Probe the photos\n\nCall `picsart_media_probe` on every photo URL before authoring. Declare its `width` and `height` on the\nasset. Those numbers decide which fit each photo gets (section 3), and they let `blur_fill` skip\nits fill on a photo whose aspect already matches the composition.\n\n```json\n\"p2\": { \"type\": \"image\", \"uri\": \"https://…/507090463024201.jpg\", \"width\": 2494, \"height\": 2560 }\n```\n\nCompare each photo's aspect (w/h) with the composition's (1080/1920 = 0.5625). `cover` crops\nthe difference away: 2296x4080 (0.563) loses nothing visible, and a 2:3 portrait such as\n2308x3462 (0.667) loses 16% of its width. A square or landscape photo such as 2494x2560 (0.974)\nwould lose 42% of its width, so it gets a blurred fill instead.\n\n## 2. A track of clips with transitions\n\nOne `track` layer holds the photos as clips, back to back. Each seam that should not be a hard\ncut gets one `transitions[]` entry keyed by `between`, the index of the gap (0 = between clips 0\nand 1):\n\n```json\n{ \"id\": \"reel\", \"start\": 0, \"duration\": 12, \"content\": { \"kind\": \"track\",\n \"clips\": [\n { \"id\": \"c1\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p1\", \"fit\": \"cover\" } },\n { \"id\": \"c2\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p2\" },\n \"looks\": [{ \"look\": \"blur_fill\", \"params\": { \"blur\": 8, \"resFactor\": 10, \"dim\": 0.25 } }] },\n { \"id\": \"c3\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p3\", \"fit\": \"cover\" } },\n { \"id\": \"c4\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p4\", \"fit\": \"cover\" } }\n ],\n \"transitions\": [\n { \"between\": 0, \"id\": \"crossfade\", \"duration\": 0.6 },\n { \"between\": 1, \"id\": \"slide\", \"duration\": 0.6, \"params\": { \"direction\": \"left\" } },\n { \"between\": 2, \"id\": \"crossfade\", \"duration\": 0.6 }\n ] } }\n```\n\n- **Timing.** The track's `duration` is the sum of its clip durations (4 x 3 = 12). A transition\n does not shorten the reel. Its window is centred on the seam, so a 0.6s crossfade at the 3.0s\n seam runs from 2.7 to 3.3.\n- **Duration rule.** Each window takes half its duration out of each clip beside it. The halves a\n clip gives up to both of its seams must fit inside that clip, or validation refuses the scene\n with `transition_window_exceeds_clip`. With 3s photos and 0.6s transitions, an inner photo\n still has 2.4s on its own.\n- **Choosing a transition.** Read `picsart_scene_capabilities({ sections: [\"transitions\"] })`. A\n closed-set param lists its allowed `enum` values, and the validator refuses anything else. Keep one\n calm transition, `crossfade`, as the default, and spend a directional one (`slide`) on the seam\n that should read as \"next\". The rendered example's `slide` `direction: \"left\"` visibly moves\n through its window.\n- **All seams the same?** `mpscene://montage` (`picsart_scene_capabilities`, section `template:mpscene://montage`) binds a clip list\n plus one `transition` id and `transitionDuration` for every seam. Author the track by hand as\n above when seams differ or a transition takes params.\n\n## 3. Cover, or contain with a blurred fill\n\n| Photo aspect vs composition | Clip content |\n|---|---|\n| Portrait, cover loses under about a fifth of the photo | `\"fit\": \"cover\"`. It fills the frame and crops the overflow. Add `align` (`\"top\"`, …) if the subject sits off-centre. |\n| Clearly different (square, landscape) | No `fit`, plus `looks: [{ \"look\": \"blur_fill\", … }]`. The whole photo is contained, and a blurred, cover-fitted copy of it fills the margins. |\n\n`blur_fill` with `blur: 8, resFactor: 10, dim: 0.25` renders the fill as an out-of-focus copy of\nthe photo under a light scrim that separates it from the contained photo. Fine detail softens,\nbut large shapes stay recognisable: the example's tree trunks still read in the margins. Raising\n`blur` to its maximum of 32 halves the fill's edge detail, and the trunks still show. The fill is\na soft backdrop, not an abstract wash. Ranges and defaults are in the `looks`\ncapability section. A look on a clip is written on the clip itself, as above, and the clip keeps\nits transitions.\n\n## 4. The title and its timing\n\nA text layer above the track. Keep the entrance editable as a preset reference in\n`content.animations`, or bake it with `picsart_scene_apply_preset` (`textAnimation:<name>`). Both render identically.\n\n```json\n{ \"id\": \"title\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1400] },\n \"animations\": { \"opacity\": { \"keyframes\": [ { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"text\", \"text\": \"OUR WINTER\",\n \"font\": { \"family\": \"gilroy-bold\", \"size\": 132 }, \"color\": \"#ffffff\", \"alignment\": \"center\",\n \"animations\": [ { \"preset\": \"fade_in_chars\", \"params\": { \"duration\": 0.8, \"stagger\": 0.4 } } ] },\n \"effects\": [ { \"id\": \"drop_shadow\", \"params\": { \"offset\": [0, 6], \"blur\": 24, \"color\": \"#000000b3\" } } ] }\n```\n\n- **An entrance starts at its layer's local time 0.** No text-animation preset takes a delay.\n To reveal later, move the layer: `start: 0.5` begins the reveal at 0.5s. Change `start` and\n `duration` together. Rendered: no ink at 0.5, partial at 0.9, the whole title by 1.3.\n- **Layer keyframes are composition seconds.** A layer's own `animations` keyframes (the opacity\n exit `2.3 → 2.6`) are composition time by default, unlike the text preset's clock. The\n validator warns (`keyframe_time_outside_window`) when one falls outside the layer's window.\n- **Gone before the first seam, by choice.** The example's title is an opening card over the\n first photo, so it leaves before anything moves under it. The layer ends at 0.5 + 2.1 = 2.6s,\n and the first seam's window opens at 2.7s (0.6s centred on 3.0). Rendered at 2.65: no title\n and no scrim. To keep a title up for the whole promo, give it and its scrim the reel's window\n instead. The scrim then has to hold over every photo, including the brightest (section 5).\n- **Wrap at a column you declare.** `wrapWidth: 900` wraps a long title inside the 900px\n between 90px side gutters. Without `wrapWidth` a line wraps at the composition's full width,\n so it can run edge to edge. \"OUR WINTER\" at 132px `gilroy-bold` draws 776px of ink, one\n line inside 900px.\n\n## 5. Readability over photos\n\nWhite text over a photo is only as readable as the brightest photo it can sit on. Measured over\nthe brightest photo in the example (snow; background median luminance 0.59), with white\n`gilroy-bold` 132px, against the median background pixel under the title (brighter patches\nfare worse). The scrim and plate rows keep the shadow on:\n\n| Treatment | Contrast vs background |\n|---|---|\n| none | 1.6 : 1 |\n| `drop_shadow` `offset [0,6]`, `blur 24`, `#000000b3` | 2.0 : 1 |\n| gradient scrim, alpha 0 → 0.6 at the text line → 0.6 at the bottom | 4.0 : 1 |\n| backing plate: 860x190 `rect`, `roundness 28`, black `fill` `opacity 0.55` | 4.0 : 1 |\n\nRules that follow:\n\n- **A shadow defines edges; it does not make text readable on a bright photo.** Keep the shadow\n for crispness, and put a scrim or a plate under any title that can land on a light photo. The\n large-text floor is 3:1, and both treatments clear it.\n- **Scrim.** A full-width shape layer beneath the title, with exactly the title's window\n (`start` 0.5, `duration` 2.1) and its own opacity fades at both ends:\n\n```json\n{ \"id\": \"scrim\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1420] },\n \"animations\": { \"opacity\": { \"keyframes\": [\n { \"time\": 0.5, \"value\": 0 }, { \"time\": 0.8, \"value\": 1 }, { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"shape\", \"items\": [\n { \"type\": \"rect\", \"position\": [0, 0], \"size\": [1080, 1000] },\n { \"type\": \"gradientFill\", \"gradientType\": \"linear\", \"startPoint\": [0, -500], \"endPoint\": [0, 500],\n \"colorStops\": [ { \"offset\": 0, \"color\": \"#000000\" }, { \"offset\": 1, \"color\": \"#000000\" } ],\n \"alphaStops\": [ { \"offset\": 0, \"alpha\": 0 }, { \"offset\": 0.5, \"alpha\": 0.6 }, { \"offset\": 1, \"alpha\": 0.6 } ] } ] } }\n```\n\n- **Placement.** A common convention for 9:16 social output is to keep text inside x 90–990 and\n y 250–1540. The example's title ink spans x 153–928 and y 1351–1447.\n\n## 6. Fonts\n\n`font.family` is a NAME. Search the catalog with `picsart_scene_fonts({ query: \"gilroy\" })` and put a\nreturned `key` in `font.family`. The example uses `gilroy-bold`, which that query returns and\nwhich is also in the list `picsart_scene_fonts()` gives with no query. Pass `licenseType: \"commercial\"` to list only faces cleared\nfor commercial use; personal-licence faces are listed too otherwise.\nThe renderer has no system fonts, so a CSS name such as `Inter` is refused with\n`unknown_font_family`, and the refusal lists the closest keys.\n\nFor a face the catalog lacks, the same `picsart_scene_fonts({ query })` call returns it in `live.fonts`. Each entry carries `asset`, a\nready-made font asset: add it to `assets` under an id, and name that id:\n\n```json\n\"assets\": { \"display\": { \"type\": \"font\", \"name\": \"Casual Fonts\", \"uri\": \"https://cdn111.picsart.com/230454663055900.ttf\" } },\n… \"font\": { \"family\": \"display\", \"size\": 64 }\n```\n\nA bare `.ttf` URL in `font.family` also renders, but it loses the font's name.\n\n## 7. Keep the context lean\n\nAuthor the scene once. Then edit it with `picsart_scene_patch` ops anchored on ids\n(`{ op: \"set\", layer: \"title\", path: \"content/text\", value: \"…\" }`) rather than re-sending the\ndocument. A patch returns the patched scene as `scene`: pass it as the next tool's\n`scene` (patch, validate, contact sheet, export). A successful patch has already been validated, so don't validate again until you\nhand-edit.\n\n## 8. Verify with one sweep\n\nAsk for the decisive moments in as few calls as possible: `picsart_scene_contact_sheet` with `times: [t1, t2, …]` and `resolution` set to the scene's `composition.width` and `composition.height`. Without `resolution` the sheet returns downscaled thumbnails, which are not for judging position. The sheet image scales every frame to fit one picture; to judge full-resolution detail, open a frame's `url`.\nThe example has twelve moments, so it takes two calls, both with `resolution: { width: 1080, height: 1920 }`:\n\n```\ntimes: [0.5, 0.9, 1.3, 1.5, 2.65, 3.0]\ntimes: [4.5, 6.0, 7.5, 9.0, 10.5, 11.967]\n```\n\n| Times | What they prove |\n|---|---|\n| 0.5, 0.9, 1.3 | The title's reveal: nothing, partial, whole |\n| 1.5, 4.5, 7.5, 10.5 | Clip midpoints: the fit / `blur_fill` framing of each photo |\n| 2.65 | Title and scrim are gone before the first seam's window (2.7) opens |\n| 3.0, 6.0, 9.0 | Seam centres: each transition is mid-flight, not a hard cut |\n| 11.967 | The last frame (`duration − 1/fps`): the reel ends on a photo, not on black |\n\nA seam centre that shows only one photo is a hard cut. Before you re-author anything, check the\ntransition's `values`.\n""---\nname: photo-slideshow\ndescription: Build a photo promo or slideshow in a scene — probe the photos, sequence them as a track of clips with transitions, fill off-aspect photos with a blurred copy, add an animated title that stays readable over any photo, choose a font, and verify with a sweep of full-resolution frames. Use when asked for a photo slideshow, photo montage, photo reel, promo video from photos, Reels/Shorts/TikTok from pictures, or a titled sequence of images.\nmetadata:\n category: authoring\n version: '1'\n---\n\n# Photo promo / slideshow\n\nAssumes the font asset from picsart_scene_fonts (a `live.fonts` entry), and that picsart_scene_patch returns the patched scene you pass to the next tool.\n\nThe most common scene job: N photos, one after another, a transition at each seam, a title.\nEvery value below was validated and rendered at 1080x1920; the whole scene is in\n[the worked example](references/worked-example.md).\n\nRelated recipes: `picsart_scene_recipe scene-video-edits` owns the track, transition-window and\n`blur_fill` detail; `picsart_scene_recipe motion-intent` chooses durations and easing.\n\n## 1. Probe the photos\n\nCall `picsart_media_probe` on every photo URL before authoring. Declare its `width` and `height` on the\nasset. Those numbers decide which fit each photo gets (section 3), and they let `blur_fill` skip\nits fill on a photo whose aspect already matches the composition.\n\n```json\n\"p2\": { \"type\": \"image\", \"uri\": \"https://…/507090463024201.jpg\", \"width\": 2494, \"height\": 2560 }\n```\n\nCompare each photo's aspect (w/h) with the composition's (1080/1920 = 0.5625). `cover` crops\nthe difference away: 2296x4080 (0.563) loses nothing visible, and a 2:3 portrait such as\n2308x3462 (0.667) loses 16% of its width. A square or landscape photo such as 2494x2560 (0.974)\nwould lose 42% of its width, so it gets a blurred fill instead.\n\n## 2. A track of clips with transitions\n\nOne `track` layer holds the photos as clips, back to back. Each seam that should not be a hard\ncut gets one `transitions[]` entry keyed by `between`, the index of the gap (0 = between clips 0\nand 1):\n\n```json\n{ \"id\": \"reel\", \"start\": 0, \"duration\": 12, \"content\": { \"kind\": \"track\",\n \"clips\": [\n { \"id\": \"c1\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p1\", \"fit\": \"cover\" } },\n { \"id\": \"c2\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p2\" },\n \"looks\": [{ \"look\": \"blur_fill\", \"params\": { \"blur\": 8, \"resFactor\": 10, \"dim\": 0.25 } }] },\n { \"id\": \"c3\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p3\", \"fit\": \"cover\" } },\n { \"id\": \"c4\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p4\", \"fit\": \"cover\" } }\n ],\n \"transitions\": [\n { \"between\": 0, \"id\": \"crossfade\", \"duration\": 0.6 },\n { \"between\": 1, \"id\": \"slide\", \"duration\": 0.6, \"params\": { \"direction\": \"left\" } },\n { \"between\": 2, \"id\": \"crossfade\", \"duration\": 0.6 }\n ] } }\n```\n\n- **Timing.** The track's `duration` is the sum of its clip durations (4 x 3 = 12). A transition\n does not shorten the reel. Its window is centred on the seam, so a 0.6s crossfade at the 3.0s\n seam runs from 2.7 to 3.3.\n- **Duration rule.** Each window takes half its duration out of each clip beside it. The halves a\n clip gives up to both of its seams must fit inside that clip, or validation refuses the scene\n with `transition_window_exceeds_clip`. With 3s photos and 0.6s transitions, an inner photo\n still has 2.4s on its own.\n- **Choosing a transition.** Read `picsart_scene_capabilities({ sections: [\"transitions\"] })`. A\n closed-set param lists its allowed `enum` values, and the validator refuses anything else. Keep one\n calm transition, `crossfade`, as the default, and spend a directional one (`slide`) on the seam\n that should read as \"next\". The rendered example's `slide` `direction: \"left\"` visibly moves\n through its window.\n- **All seams the same?** `scene://montage` (`picsart_scene_capabilities`, section `template:scene://montage`) binds a clip list\n plus one `transition` id and `transitionDuration` for every seam. Author the track by hand as\n above when seams differ or a transition takes params.\n\n## 3. Cover, or contain with a blurred fill\n\n| Photo aspect vs composition | Clip content |\n|---|---|\n| Portrait, cover loses under about a fifth of the photo | `\"fit\": \"cover\"`. It fills the frame and crops the overflow. Add `align` (`\"top\"`, …) if the subject sits off-centre. |\n| Clearly different (square, landscape) | No `fit`, plus `looks: [{ \"look\": \"blur_fill\", … }]`. The whole photo is contained, and a blurred, cover-fitted copy of it fills the margins. |\n\n`blur_fill` with `blur: 8, resFactor: 10, dim: 0.25` renders the fill as an out-of-focus copy of\nthe photo under a light scrim that separates it from the contained photo. Fine detail softens,\nbut large shapes stay recognisable: the example's tree trunks still read in the margins. Raising\n`blur` to its maximum of 32 halves the fill's edge detail, and the trunks still show. The fill is\na soft backdrop, not an abstract wash. Ranges and defaults are in the `looks`\ncapability section. A look on a clip is written on the clip itself, as above, and the clip keeps\nits transitions.\n\n## 4. The title and its timing\n\nA text layer above the track. Keep the entrance editable as a preset reference in\n`content.animations`, or bake it with `picsart_scene_apply_preset` (`textAnimation:<name>`). Both render identically.\n\n```json\n{ \"id\": \"title\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1400] },\n \"animations\": { \"opacity\": { \"keyframes\": [ { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"text\", \"text\": \"OUR WINTER\",\n \"font\": { \"family\": \"gilroy-bold\", \"size\": 132 }, \"color\": \"#ffffff\", \"alignment\": \"center\",\n \"animations\": [ { \"preset\": \"fade_in_chars\", \"params\": { \"duration\": 0.8, \"stagger\": 0.4 } } ] },\n \"effects\": [ { \"id\": \"drop_shadow\", \"params\": { \"offset\": [0, 6], \"blur\": 24, \"color\": \"#000000b3\" } } ] }\n```\n\n- **An entrance starts at its layer's local time 0.** No text-animation preset takes a delay.\n To reveal later, move the layer: `start: 0.5` begins the reveal at 0.5s. Change `start` and\n `duration` together. Rendered: no ink at 0.5, partial at 0.9, the whole title by 1.3.\n- **Layer keyframes are composition seconds.** A layer's own `animations` keyframes (the opacity\n exit `2.3 → 2.6`) are composition time by default, unlike the text preset's clock. The\n validator warns (`keyframe_time_outside_window`) when one falls outside the layer's window.\n- **Gone before the first seam, by choice.** The example's title is an opening card over the\n first photo, so it leaves before anything moves under it. The layer ends at 0.5 + 2.1 = 2.6s,\n and the first seam's window opens at 2.7s (0.6s centred on 3.0). Rendered at 2.65: no title\n and no scrim. To keep a title up for the whole promo, give it and its scrim the reel's window\n instead. The scrim then has to hold over every photo, including the brightest (section 5).\n- **Wrap at a column you declare.** `wrapWidth: 900` wraps a long title inside the 900px\n between 90px side gutters. Without `wrapWidth` a line wraps at the composition's full width,\n so it can run edge to edge. \"OUR WINTER\" at 132px `gilroy-bold` draws 776px of ink, one\n line inside 900px.\n\n## 5. Readability over photos\n\nWhite text over a photo is only as readable as the brightest photo it can sit on. Measured over\nthe brightest photo in the example (snow; background median luminance 0.59), with white\n`gilroy-bold` 132px, against the median background pixel under the title (brighter patches\nfare worse). The scrim and plate rows keep the shadow on:\n\n| Treatment | Contrast vs background |\n|---|---|\n| none | 1.6 : 1 |\n| `drop_shadow` `offset [0,6]`, `blur 24`, `#000000b3` | 2.0 : 1 |\n| gradient scrim, alpha 0 → 0.6 at the text line → 0.6 at the bottom | 4.0 : 1 |\n| backing plate: 860x190 `rect`, `roundness 28`, black `fill` `opacity 0.55` | 4.0 : 1 |\n\nRules that follow:\n\n- **A shadow defines edges; it does not make text readable on a bright photo.** Keep the shadow\n for crispness, and put a scrim or a plate under any title that can land on a light photo. The\n large-text floor is 3:1, and both treatments clear it.\n- **Scrim.** A full-width shape layer beneath the title, with exactly the title's window\n (`start` 0.5, `duration` 2.1) and its own opacity fades at both ends:\n\n```json\n{ \"id\": \"scrim\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1420] },\n \"animations\": { \"opacity\": { \"keyframes\": [\n { \"time\": 0.5, \"value\": 0 }, { \"time\": 0.8, \"value\": 1 }, { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"shape\", \"items\": [\n { \"type\": \"rect\", \"position\": [0, 0], \"size\": [1080, 1000] },\n { \"type\": \"gradientFill\", \"gradientType\": \"linear\", \"startPoint\": [0, -500], \"endPoint\": [0, 500],\n \"colorStops\": [ { \"offset\": 0, \"color\": \"#000000\" }, { \"offset\": 1, \"color\": \"#000000\" } ],\n \"alphaStops\": [ { \"offset\": 0, \"alpha\": 0 }, { \"offset\": 0.5, \"alpha\": 0.6 }, { \"offset\": 1, \"alpha\": 0.6 } ] } ] } }\n```\n\n- **Placement.** A common convention for 9:16 social output is to keep text inside x 90–990 and\n y 250–1540. The example's title ink spans x 153–928 and y 1351–1447.\n\n## 6. Fonts\n\n`font.family` is a NAME. Search the catalog with `picsart_scene_fonts({ query: \"gilroy\" })` and put a\nreturned `key` in `font.family`. The example uses `gilroy-bold`, which that query returns and\nwhich is also in the list `picsart_scene_fonts()` gives with no query. Pass `licenseType: \"commercial\"` to list only faces cleared\nfor commercial use; personal-licence faces are listed too otherwise.\nThe renderer has no system fonts, so a CSS name such as `Inter` is refused with\n`unknown_font_family`, and the refusal lists the closest keys.\n\nFor a face the catalog lacks, the same `picsart_scene_fonts({ query })` call returns it in `live.fonts`. Each entry carries `asset`, a\nready-made font asset: add it to `assets` under an id, and name that id:\n\n```json\n\"assets\": { \"display\": { \"type\": \"font\", \"name\": \"Casual Fonts\", \"uri\": \"https://cdn111.picsart.com/230454663055900.ttf\" } },\n… \"font\": { \"family\": \"display\", \"size\": 64 }\n```\n\nA bare `.ttf` URL in `font.family` also renders, but it loses the font's name.\n\n## 7. Keep the context lean\n\nAuthor the scene once. Then edit it with `picsart_scene_patch` ops anchored on ids\n(`{ op: \"set\", layer: \"title\", path: \"content/text\", value: \"…\" }`) rather than re-sending the\ndocument. A patch returns the patched scene as `scene`: pass it as the next tool's\n`scene` (patch, validate, contact sheet, export). A successful patch has already been validated, so don't validate again until you\nhand-edit.\n\n## 8. Verify with one sweep\n\nAsk for the decisive moments in as few calls as possible: `picsart_scene_contact_sheet` with `times: [t1, t2, …]` and `resolution` set to the scene's `composition.width` and `composition.height`. Without `resolution` the sheet returns downscaled thumbnails, which are not for judging position. The sheet image scales every frame to fit one picture; to judge full-resolution detail, open a frame's `url`.\nThe example has twelve moments, so it takes two calls, both with `resolution: { width: 1080, height: 1920 }`:\n\n```\ntimes: [0.5, 0.9, 1.3, 1.5, 2.65, 3.0]\ntimes: [4.5, 6.0, 7.5, 9.0, 10.5, 11.967]\n```\n\n| Times | What they prove |\n|---|---|\n| 0.5, 0.9, 1.3 | The title's reveal: nothing, partial, whole |\n| 1.5, 4.5, 7.5, 10.5 | Clip midpoints: the fit / `blur_fill` framing of each photo |\n| 2.65 | Title and scrim are gone before the first seam's window (2.7) opens |\n| 3.0, 6.0, 9.0 | Seam centres: each transition is mid-flight, not a hard cut |\n| 11.967 | The last frame (`duration − 1/fps`): the reel ends on a photo, not on black |\n\nA seam centre that shows only one photo is a hard cut. Before you re-author anything, check the\ntransition's `values`.\n"Full snapshot data
{
"description": "Build a photo promo or slideshow in a scene — probe the photos, sequence them as a track of clips with transitions, fill off-aspect photos with a blurred copy, add an animated title that stays readable over any photo, choose a font, and verify with a sweep of full-resolution frames. Use when asked for a photo slideshow, photo montage, photo reel, promo video from photos, Reels/Shorts/TikTok from pictures, or a titled sequence of images.",
"included_files": [
{
"relative_path": "references/worked-example.md",
"size_in_bytes": 4616
}
],
"name": "photo-slideshow",
"skill_md_contents": "---\nname: photo-slideshow\ndescription: Build a photo promo or slideshow in a scene — probe the photos, sequence them as a track of clips with transitions, fill off-aspect photos with a blurred copy, add an animated title that stays readable over any photo, choose a font, and verify with a sweep of full-resolution frames. Use when asked for a photo slideshow, photo montage, photo reel, promo video from photos, Reels/Shorts/TikTok from pictures, or a titled sequence of images.\nmetadata:\n category: authoring\n version: '1'\n---\n\n# Photo promo / slideshow\n\nAssumes the font asset from picsart_scene_fonts (a `live.fonts` entry), and that picsart_scene_patch returns the patched scene you pass to the next tool.\n\nThe most common scene job: N photos, one after another, a transition at each seam, a title.\nEvery value below was validated and rendered at 1080x1920; the whole scene is in\n[the worked example](references/worked-example.md).\n\nRelated recipes: `picsart_scene_recipe scene-video-edits` owns the track, transition-window and\n`blur_fill` detail; `picsart_scene_recipe motion-intent` chooses durations and easing.\n\n## 1. Probe the photos\n\nCall `picsart_media_probe` on every photo URL before authoring. Declare its `width` and `height` on the\nasset. Those numbers decide which fit each photo gets (section 3), and they let `blur_fill` skip\nits fill on a photo whose aspect already matches the composition.\n\n```json\n\"p2\": { \"type\": \"image\", \"uri\": \"https://…/507090463024201.jpg\", \"width\": 2494, \"height\": 2560 }\n```\n\nCompare each photo's aspect (w/h) with the composition's (1080/1920 = 0.5625). `cover` crops\nthe difference away: 2296x4080 (0.563) loses nothing visible, and a 2:3 portrait such as\n2308x3462 (0.667) loses 16% of its width. A square or landscape photo such as 2494x2560 (0.974)\nwould lose 42% of its width, so it gets a blurred fill instead.\n\n## 2. A track of clips with transitions\n\nOne `track` layer holds the photos as clips, back to back. Each seam that should not be a hard\ncut gets one `transitions[]` entry keyed by `between`, the index of the gap (0 = between clips 0\nand 1):\n\n```json\n{ \"id\": \"reel\", \"start\": 0, \"duration\": 12, \"content\": { \"kind\": \"track\",\n \"clips\": [\n { \"id\": \"c1\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p1\", \"fit\": \"cover\" } },\n { \"id\": \"c2\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p2\" },\n \"looks\": [{ \"look\": \"blur_fill\", \"params\": { \"blur\": 8, \"resFactor\": 10, \"dim\": 0.25 } }] },\n { \"id\": \"c3\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p3\", \"fit\": \"cover\" } },\n { \"id\": \"c4\", \"duration\": 3, \"content\": { \"kind\": \"media\", \"assetId\": \"p4\", \"fit\": \"cover\" } }\n ],\n \"transitions\": [\n { \"between\": 0, \"id\": \"crossfade\", \"duration\": 0.6 },\n { \"between\": 1, \"id\": \"slide\", \"duration\": 0.6, \"params\": { \"direction\": \"left\" } },\n { \"between\": 2, \"id\": \"crossfade\", \"duration\": 0.6 }\n ] } }\n```\n\n- **Timing.** The track's `duration` is the sum of its clip durations (4 x 3 = 12). A transition\n does not shorten the reel. Its window is centred on the seam, so a 0.6s crossfade at the 3.0s\n seam runs from 2.7 to 3.3.\n- **Duration rule.** Each window takes half its duration out of each clip beside it. The halves a\n clip gives up to both of its seams must fit inside that clip, or validation refuses the scene\n with `transition_window_exceeds_clip`. With 3s photos and 0.6s transitions, an inner photo\n still has 2.4s on its own.\n- **Choosing a transition.** Read `picsart_scene_capabilities({ sections: [\"transitions\"] })`. A\n closed-set param lists its allowed `enum` values, and the validator refuses anything else. Keep one\n calm transition, `crossfade`, as the default, and spend a directional one (`slide`) on the seam\n that should read as \"next\". The rendered example's `slide` `direction: \"left\"` visibly moves\n through its window.\n- **All seams the same?** `scene://montage` (`picsart_scene_capabilities`, section `template:scene://montage`) binds a clip list\n plus one `transition` id and `transitionDuration` for every seam. Author the track by hand as\n above when seams differ or a transition takes params.\n\n## 3. Cover, or contain with a blurred fill\n\n| Photo aspect vs composition | Clip content |\n|---|---|\n| Portrait, cover loses under about a fifth of the photo | `\"fit\": \"cover\"`. It fills the frame and crops the overflow. Add `align` (`\"top\"`, …) if the subject sits off-centre. |\n| Clearly different (square, landscape) | No `fit`, plus `looks: [{ \"look\": \"blur_fill\", … }]`. The whole photo is contained, and a blurred, cover-fitted copy of it fills the margins. |\n\n`blur_fill` with `blur: 8, resFactor: 10, dim: 0.25` renders the fill as an out-of-focus copy of\nthe photo under a light scrim that separates it from the contained photo. Fine detail softens,\nbut large shapes stay recognisable: the example's tree trunks still read in the margins. Raising\n`blur` to its maximum of 32 halves the fill's edge detail, and the trunks still show. The fill is\na soft backdrop, not an abstract wash. Ranges and defaults are in the `looks`\ncapability section. A look on a clip is written on the clip itself, as above, and the clip keeps\nits transitions.\n\n## 4. The title and its timing\n\nA text layer above the track. Keep the entrance editable as a preset reference in\n`content.animations`, or bake it with `picsart_scene_apply_preset` (`textAnimation:<name>`). Both render identically.\n\n```json\n{ \"id\": \"title\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1400] },\n \"animations\": { \"opacity\": { \"keyframes\": [ { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"text\", \"text\": \"OUR WINTER\",\n \"font\": { \"family\": \"gilroy-bold\", \"size\": 132 }, \"color\": \"#ffffff\", \"alignment\": \"center\",\n \"animations\": [ { \"preset\": \"fade_in_chars\", \"params\": { \"duration\": 0.8, \"stagger\": 0.4 } } ] },\n \"effects\": [ { \"id\": \"drop_shadow\", \"params\": { \"offset\": [0, 6], \"blur\": 24, \"color\": \"#000000b3\" } } ] }\n```\n\n- **An entrance starts at its layer's local time 0.** No text-animation preset takes a delay.\n To reveal later, move the layer: `start: 0.5` begins the reveal at 0.5s. Change `start` and\n `duration` together. Rendered: no ink at 0.5, partial at 0.9, the whole title by 1.3.\n- **Layer keyframes are composition seconds.** A layer's own `animations` keyframes (the opacity\n exit `2.3 → 2.6`) are composition time by default, unlike the text preset's clock. The\n validator warns (`keyframe_time_outside_window`) when one falls outside the layer's window.\n- **Gone before the first seam, by choice.** The example's title is an opening card over the\n first photo, so it leaves before anything moves under it. The layer ends at 0.5 + 2.1 = 2.6s,\n and the first seam's window opens at 2.7s (0.6s centred on 3.0). Rendered at 2.65: no title\n and no scrim. To keep a title up for the whole promo, give it and its scrim the reel's window\n instead. The scrim then has to hold over every photo, including the brightest (section 5).\n- **Wrap at a column you declare.** `wrapWidth: 900` wraps a long title inside the 900px\n between 90px side gutters. Without `wrapWidth` a line wraps at the composition's full width,\n so it can run edge to edge. \"OUR WINTER\" at 132px `gilroy-bold` draws 776px of ink, one\n line inside 900px.\n\n## 5. Readability over photos\n\nWhite text over a photo is only as readable as the brightest photo it can sit on. Measured over\nthe brightest photo in the example (snow; background median luminance 0.59), with white\n`gilroy-bold` 132px, against the median background pixel under the title (brighter patches\nfare worse). The scrim and plate rows keep the shadow on:\n\n| Treatment | Contrast vs background |\n|---|---|\n| none | 1.6 : 1 |\n| `drop_shadow` `offset [0,6]`, `blur 24`, `#000000b3` | 2.0 : 1 |\n| gradient scrim, alpha 0 → 0.6 at the text line → 0.6 at the bottom | 4.0 : 1 |\n| backing plate: 860x190 `rect`, `roundness 28`, black `fill` `opacity 0.55` | 4.0 : 1 |\n\nRules that follow:\n\n- **A shadow defines edges; it does not make text readable on a bright photo.** Keep the shadow\n for crispness, and put a scrim or a plate under any title that can land on a light photo. The\n large-text floor is 3:1, and both treatments clear it.\n- **Scrim.** A full-width shape layer beneath the title, with exactly the title's window\n (`start` 0.5, `duration` 2.1) and its own opacity fades at both ends:\n\n```json\n{ \"id\": \"scrim\", \"start\": 0.5, \"duration\": 2.1, \"transform\": { \"position\": [540, 1420] },\n \"animations\": { \"opacity\": { \"keyframes\": [\n { \"time\": 0.5, \"value\": 0 }, { \"time\": 0.8, \"value\": 1 }, { \"time\": 2.3, \"value\": 1 }, { \"time\": 2.6, \"value\": 0 } ] } },\n \"content\": { \"kind\": \"shape\", \"items\": [\n { \"type\": \"rect\", \"position\": [0, 0], \"size\": [1080, 1000] },\n { \"type\": \"gradientFill\", \"gradientType\": \"linear\", \"startPoint\": [0, -500], \"endPoint\": [0, 500],\n \"colorStops\": [ { \"offset\": 0, \"color\": \"#000000\" }, { \"offset\": 1, \"color\": \"#000000\" } ],\n \"alphaStops\": [ { \"offset\": 0, \"alpha\": 0 }, { \"offset\": 0.5, \"alpha\": 0.6 }, { \"offset\": 1, \"alpha\": 0.6 } ] } ] } }\n```\n\n- **Placement.** A common convention for 9:16 social output is to keep text inside x 90–990 and\n y 250–1540. The example's title ink spans x 153–928 and y 1351–1447.\n\n## 6. Fonts\n\n`font.family` is a NAME. Search the catalog with `picsart_scene_fonts({ query: \"gilroy\" })` and put a\nreturned `key` in `font.family`. The example uses `gilroy-bold`, which that query returns and\nwhich is also in the list `picsart_scene_fonts()` gives with no query. Pass `licenseType: \"commercial\"` to list only faces cleared\nfor commercial use; personal-licence faces are listed too otherwise.\nThe renderer has no system fonts, so a CSS name such as `Inter` is refused with\n`unknown_font_family`, and the refusal lists the closest keys.\n\nFor a face the catalog lacks, the same `picsart_scene_fonts({ query })` call returns it in `live.fonts`. Each entry carries `asset`, a\nready-made font asset: add it to `assets` under an id, and name that id:\n\n```json\n\"assets\": { \"display\": { \"type\": \"font\", \"name\": \"Casual Fonts\", \"uri\": \"https://cdn111.picsart.com/230454663055900.ttf\" } },\n… \"font\": { \"family\": \"display\", \"size\": 64 }\n```\n\nA bare `.ttf` URL in `font.family` also renders, but it loses the font's name.\n\n## 7. Keep the context lean\n\nAuthor the scene once. Then edit it with `picsart_scene_patch` ops anchored on ids\n(`{ op: \"set\", layer: \"title\", path: \"content/text\", value: \"…\" }`) rather than re-sending the\ndocument. A patch returns the patched scene as `scene`: pass it as the next tool's\n`scene` (patch, validate, contact sheet, export). A successful patch has already been validated, so don't validate again until you\nhand-edit.\n\n## 8. Verify with one sweep\n\nAsk for the decisive moments in as few calls as possible: `picsart_scene_contact_sheet` with `times: [t1, t2, …]` and `resolution` set to the scene's `composition.width` and `composition.height`. Without `resolution` the sheet returns downscaled thumbnails, which are not for judging position. The sheet image scales every frame to fit one picture; to judge full-resolution detail, open a frame's `url`.\nThe example has twelve moments, so it takes two calls, both with `resolution: { width: 1080, height: 1920 }`:\n\n```\ntimes: [0.5, 0.9, 1.3, 1.5, 2.65, 3.0]\ntimes: [4.5, 6.0, 7.5, 9.0, 10.5, 11.967]\n```\n\n| Times | What they prove |\n|---|---|\n| 0.5, 0.9, 1.3 | The title's reveal: nothing, partial, whole |\n| 1.5, 4.5, 7.5, 10.5 | Clip midpoints: the fit / `blur_fill` framing of each photo |\n| 2.65 | Title and scrim are gone before the first seam's window (2.7) opens |\n| 3.0, 6.0, 9.0 | Seam centres: each transition is mid-flight, not a hard cut |\n| 11.967 | The last frame (`duration − 1/fps`): the reel ends on a photo, not on black |\n\nA seam centre that shows only one photo is a hard cut. Before you re-author anything, check the\ntransition's `values`.\n"
}SHA-256 of public snapshot: bddf678dfc9867efc4b1ab14de77f4b43e7d9fb0b0411e47d96e282b8513feb9