Logospell

Previous value: -"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Write each variation as plain text, with no list marker such as \"1.\" or \"-\" in front, no square brackets, and no invisible characters."

Previous value: -"Either a list of subject names (e.g. [\"home\", \"search\"]) or objects with description and filename (e.g. [{\"description\": \"compass rose\", \"filename\": \"overview.webp\"}]). Each subject must name a drawable subject and be distinct: entries differing only in case, punctuation, or spacing are rejected as the same subject. A subject with no Latin letters or numbers (a name written entirely in another script) needs the object form with a filename, since delivered files are named in ASCII. Subject text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"Either a list of subject names (e.g. [\"home\", \"search\"]) or objects with description and filename (e.g. [{\"description\": \"compass rose\", \"filename\": \"overview.webp\"}]). Each subject must name a drawable subject and be distinct: entries differing only in case, punctuation, or spacing are rejected as the same subject. A subject with no Latin letters or numbers (a name written entirely in another script) needs the object form with a filename, since delivered files are named in ASCII. Write each subject as plain text, with no list marker such as \"1.\" or \"-\" in front, no square brackets, and no invisible characters."

Previous value: -"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Write each variation as plain text, with no list marker such as \"1.\" or \"-\" in front, no square brackets, and no invisible characters."

Previous value: -"Either a list of subject names (e.g. [\"home\", \"search\"]) or objects with description and filename (e.g. [{\"description\": \"compass rose\", \"filename\": \"overview.webp\"}]). Each subject must name a drawable subject and be distinct: entries differing only in case, punctuation, or spacing are rejected as the same subject. A subject with no Latin letters or numbers (a name written entirely in another script) needs the object form with a filename, since delivered files are named in ASCII. Subject text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"Either a list of subject names (e.g. [\"home\", \"search\"]) or objects with description and filename (e.g. [{\"description\": \"compass rose\", \"filename\": \"overview.webp\"}]). Each subject must name a drawable subject and be distinct: entries differing only in case, punctuation, or spacing are rejected as the same subject. A subject with no Latin letters or numbers (a name written entirely in another script) needs the object form with a filename, since delivered files are named in ASCII. Write each subject as plain text, with no list marker such as \"1.\" or \"-\" in front, no square brackets, and no invisible characters."

Previous value: -"What each illustration shows, one entry per picture: either a list of scene descriptions or objects with description and filename (e.g. [{\"description\": \"a harbor market at dawn\", \"filename\": \"hero.webp\"}]). A scene is prose and may name a setting, a moment, the light and the camera. Entries must describe distinct pictures; without a filename, the file is named from the start of its scene."New value: +"What each illustration shows, one entry per illustration: either a list of scene descriptions or objects with description and filename (e.g. [{\"description\": \"a harbor market at dawn\", \"filename\": \"hero.webp\"}]). A scene is prose and may name a setting, a moment, the light and the camera. Entries must describe distinct illustrations; without a filename, the file is named from the start of its scene."

Previous value: -"Present only when the request was rejected because some scenes do not appear to describe distinct pictures: the exact rejected entries. No generation ran and nothing was charged; revise or remove them and resubmit."New value: +"Present only when the request was rejected because some scenes do not appear to describe distinct illustrations: the exact rejected entries. No generation ran and nothing was charged; revise or remove them and resubmit."

Previous value: -"What each illustration shows, one entry per picture: either a list of scene descriptions or objects with description and filename (e.g. [{\"description\": \"a harbor market at dawn\", \"filename\": \"hero.webp\"}]). A scene is prose and may name a setting, a moment, the light and the camera. Entries must describe distinct pictures; without a filename, the file is named from the start of its scene."New value: +"What each illustration shows, one entry per illustration: either a list of scene descriptions or objects with description and filename (e.g. [{\"description\": \"a harbor market at dawn\", \"filename\": \"hero.webp\"}]). A scene is prose and may name a setting, a moment, the light and the camera. Entries must describe distinct illustrations; without a filename, the file is named from the start of its scene."

Previous value: -"Present only when the request was rejected because some scenes do not appear to describe distinct pictures: the exact rejected entries. No generation ran and nothing was charged; revise or remove them and resubmit."New value: +"Present only when the request was rejected because some scenes do not appear to describe distinct illustrations: the exact rejected entries. No generation ran and nothing was charged; revise or remove them and resubmit."

Added value: +{
+  "description": "New file size limit for each image, in KB, webp only: each image is encoded under it as on the set tools, its quality and the precision of its transparent edges lowered together only where needed, down to quality 70; a set below 70 keeps its quality and lowers only its edges. An image still over the limit is named in the result. 0 removes the limit. Left out, the current limit stays.",
+  "type": [
+    "null",
+    "integer"
+  ]
+}

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Previous value: -"The delivery levers now in force: width, height, canvas, minimumMargin, sizing, format, quality, background; an illustration set has only width, height, format and quality."New value: +"The delivery levers now in force: width, height, canvas, minimumMargin, sizing, format, quality, background, and maxKB when a file size limit is set; an illustration set has only width, height, format and quality."

Added value: +{
+  "type": "integer"
+}

Previous value: -"The id of any batch in the set to extend: the random segment of its download URL (.../download/<id>/images.zip), also returned by list_recent_generations. The new batch is generated exactly as that set: the same tool, character text and character references, and the named batch's background, size, format, quality, margin and sizing."New value: +"The id of any batch in the set to extend: the random segment of its download URL (.../download/<id>/images.zip), also returned by list_recent_generations. The new batch is generated exactly as that set: the same tool, character text and character references, and the named batch's background, size, format, quality, margin, sizing and file size limit."

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Previous value: -"The id of any batch in the set to extend: the random segment of its download URL (.../download/<id>/images.zip), also returned by list_recent_generations. The new batch is generated exactly as that set: the same tool, style text and style references, and the named batch's background, size, format, quality, margin and sizing."New value: +"The id of any batch in the set to extend: the random segment of its download URL (.../download/<id>/images.zip), also returned by list_recent_generations. The new batch is generated exactly as that set: the same tool, style text and style references, and the named batch's background, size, format, quality, margin, sizing and file size limit."

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Added value: +{
+  "description": "A file size limit for each image, in KB (1 KB = 1024 bytes), 10 to 10240; webp only (rejected with png or jpg). An image that fits keeps the quality set above; one that does not has its quality and the precision of its transparent edges lowered together, 5 quality points at a time down to 70, until it fits (a set below 70 keeps its quality and lowers only its edges), so images in a set can land at different qualities and the faintest edges of a busy transparent image can soften. An image still over the limit at the last step is delivered anyway and named in the result. For platforms that cap each file's size. Omit for no limit.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Added value: +{
+  "description": "A file size limit for each image, in KB (1 KB = 1024 bytes), 10 to 10240; webp only (rejected with png or jpg). An image that fits keeps the quality set above; one that does not has its quality and the precision of its transparent edges lowered together, 5 quality points at a time down to 70, until it fits (a set below 70 keeps its quality and lowers only its edges), so images in a set can land at different qualities and the faintest edges of a busy transparent image can soften. An image still over the limit at the last step is delivered anyway and named in the result. For platforms that cap each file's size. Omit for no limit.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image file's size in bytes.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): how many transparency levels this image kept; 256 is exact.",
+  "type": "integer"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): true when this image is still over the limit at the lowest step (quality 70, or the set's own when that is lower).",
+  "type": "boolean"
+}

Added value: +{
+  "description": "Under a file size limit (maxKB): the quality this image was delivered at.",
+  "type": "integer"
+}

Previous value: -"The delivery levers now in force (width, height, canvas, minimumMargin, sizing, format, quality, background; an illustration set has width, height, format and quality): the first delivery's until edit_set changes them. Absent on sets from before editing existed."New value: +"The delivery levers now in force (width, height, canvas, minimumMargin, sizing, format, quality, background, and maxKB when a file size limit is set; an illustration set has width, height, format and quality): the first delivery's until edit_set changes them. Absent on sets from before editing existed."

Added value: +{
+  "type": "integer"
+}

Previous value: -"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (the style or character, the list and the references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, sizing, format, quality) are the current delivery, which edit_set rewrites, so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its background is the color the set was generated on, or transparent (a set generated transparent stays transparent here after an edit changes its background to a color; levers holds the color). Its shape follows the tool named in its own tool field. Image sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background (a color, or transparent), and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places; illustration sets carry style, styleReferences, scenes, width, height, format and quality. Read each entry's description (subjects[], variations[] or scenes[]) to reproduce a set: an entry given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."New value: +"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (the style or character, the list and the references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, sizing, format, quality, maxKB) are the current delivery, which edit_set rewrites, so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its background is the color the set was generated on, or transparent (a set generated transparent stays transparent here after an edit changes its background to a color; levers holds the color). Its shape follows the tool named in its own tool field. Image sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background (a color, or transparent), and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places; illustration sets carry style, styleReferences, scenes, width, height, format and quality. Read each entry's description (subjects[], variations[] or scenes[]) to reproduce a set: an entry given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."

Previous value: -"png, webp, or jpg. Left out, the set's current format. iOS asset catalogs take no WebP, so a webp export's iOS tree is PNG at the same pixels (the ledger says so). jpg has no alpha: rejected for a transparent set unless the set is currently composed over a color."New value: +"png, webp, or jpg. Left out, the set's current format. iOS asset catalogs take no WebP, so a webp export's iOS tree is PNG at the same pixels (the ledger says so). jpg has no alpha: rejected while the set's background is transparent."

Previous value: -"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a transparent set is png or webp."New value: +"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a set delivered transparent is png or webp."

Previous value: -"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a transparent set is png or webp."New value: +"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a set delivered transparent is png or webp."

Previous value: -"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (the style or character, the list and the references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, sizing, format, quality) are the current delivery, which edit_set rewrites, so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its background is the color the set was generated on, or transparent (an edit that composes a transparent set over a color leaves it transparent here; levers holds the color). Its shape follows the tool named in its own tool field. Image sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background (a color, or transparent), and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places; illustration sets carry style, styleReferences, scenes, width, height, format and quality. Read each entry's description (subjects[], variations[] or scenes[]) to reproduce a set: an entry given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."New value: +"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (the style or character, the list and the references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, sizing, format, quality) are the current delivery, which edit_set rewrites, so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its background is the color the set was generated on, or transparent (a set generated transparent stays transparent here after an edit changes its background to a color; levers holds the color). Its shape follows the tool named in its own tool field. Image sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background (a color, or transparent), and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places; illustration sets carry style, styleReferences, scenes, width, height, format and quality. Read each entry's description (subjects[], variations[] or scenes[]) to reproduce a set: an entry given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."

Previous value: -"Transparent sets only: a #RRGGBB color composes every image over it and delivers an opaque set; \"transparent\" restores the alpha. Left out, the current background stays. Rejected on a solid-background set, whose color is in its pixels and cannot change."New value: +"Character sets and transparent image sets only: a #RRGGBB color composes every image over it and delivers an opaque set; \"transparent\" delivers the images with their alpha. Left out, the current background stays. Rejected on an image set generated on a color, whose color is in its pixels and cannot change."

Previous value: -"New format: png, webp, or jpg. Left out, the current format stays. jpg has no alpha: on a transparent set it composes the images over white unless a background color is in force (given in the same call or kept from an earlier edit)."New value: +"New format: png, webp, or jpg. Left out, the current format stays. jpg has no alpha: on a set delivered transparent it composes the images over white unless a background color is in force (given in the same call or kept from an earlier edit)."

Previous value: -"Ids of the generations whose delivered images seeded this one's references - the set lineage. Absent when this generation extended nothing."New value: +"Ids of the generations this one came from: for a batch made with an extend tool, its set's first batch; otherwise the generations its sourced references were copied from (create_reference's sourceGeneration). Only a parent made by the same tool on the same kind of background, a color or transparent, is in this one's set; any other only supplied reference images. Absent when neither applies."

Previous value: -"Ids of the generations whose delivered images seeded this one's references: the set lineage, for gathering a whole set's ids."New value: +"Ids of the generations this one came from: for a batch made with an extend tool, its set's first batch; otherwise the generations its sourced references were copied from (create_reference's sourceGeneration). Only a parent made by the same tool on the same kind of background, a color or transparent, is in this one's set; any other only supplied reference images. To gather a whole set's ids, follow only those (get_generations' promptJSON shows each one's tool and background)."

Previous value: -"Optional, with sourceGeneration: the delivered image filename to use as the reference, exactly as the generation's result, its manifest, or get_generations (the subjects in promptJSON) lists it (e.g. \"a_lotus_cradling_a_glowing_pearl.png\"). An image larger than the reference limits is downscaled to fit automatically."New value: +"Optional, with sourceGeneration: the delivered image filename to use as the reference, exactly as the generation's result or get_generations (the subjects, variations or scenes in promptJSON) lists it (e.g. \"a_lotus_cradling_a_glowing_pearl.png\"). An image larger than the reference limits is downscaled to fit automatically."

Previous value: -"The background color used; absent for transparent sets."New value: +"The background color used, or transparent."

Previous value: -"The generated images: variation description, filename inside the zip, and pixel width and height."New value: +"The generated images: each one's file name inside the zip, its variation, and its pixel width and height."

Added value: +{
+  "description": "The subject, variation or scene this image was made from, as the call gave it.",
+  "type": "string"
+}

Added value: +"The image's file name inside the zip."

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  "name",
-  "filename"
-]New value: +[
+  "filename",
+  "description"
+]

Previous value: -"The background color used; absent for transparent sets."New value: +"The background color used, or transparent."

Previous value: -"The generated images: subject name, filename inside the zip, and pixel width and height."New value: +"The generated images: each one's file name inside the zip, its subject, and its pixel width and height."

Added value: +{
+  "description": "The subject, variation or scene this image was made from, as the call gave it.",
+  "type": "string"
+}

Added value: +"The image's file name inside the zip."

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  "name",
-  "filename"
-]New value: +[
+  "filename",
+  "description"
+]

Previous value: -"Present only on a validation suggestion: the cleaned style text, for review. An empty string means the cleanup removed the style entirely (nothing in it was usable as a style) - replace it, or use styleReferences. Absent on refs-only requests. No generation ran and nothing was charged."New value: +"Present only on a validation suggestion: the cleaned style text, for review. An empty string means the cleanup removed the style entirely (nothing in it was usable as a style) - replace it, or use styleReferences. Absent when the style was not checked (references only, or an extension). No generation ran and nothing was charged."

Previous value: -"Background as a 6-char hex color #RRGGBB (e.g. #ffffff, #2c3e50). Default is #ffffff. For transparent output, call the generate_transparent_character_set tool instead - this tool only produces solid-color backgrounds. Do not mention background in the character or variation descriptions."New value: +"The background every image sits on: a 6-char hex color #RRGGBB (e.g. #ffffff, #2c3e50), or \"transparent\" for images with no background that drop onto any backdrop. Default is #ffffff. Do not mention background in the character or variation descriptions."

Previous value: -"Output format: png, jpg, or webp. Defaults to png."New value: +"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a transparent set is png or webp."

Previous value: -"The background color used; absent for transparent sets."New value: +"The background color used, or transparent."

Previous value: -"The generated images: variation description, filename inside the zip, and pixel width and height."New value: +"The generated images: each one's file name inside the zip, its variation, and its pixel width and height."

Added value: +{
+  "description": "The subject, variation or scene this image was made from, as the call gave it.",
+  "type": "string"
+}

Added value: +"The image's file name inside the zip."

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  "name",
-  "filename"
-]New value: +[
+  "filename",
+  "description"
+]

Previous value: -"Background as a 6-char hex color #RRGGBB (e.g. #ffffff, #2c3e50). Default is #ffffff. For transparent output, call the generate_transparent_image_set tool instead - this tool only produces solid-color backgrounds. Do not mention background in the style or subject descriptions."New value: +"The background every image sits on: a 6-char hex color #RRGGBB (e.g. #ffffff, #2c3e50), or \"transparent\" for images with no background that drop onto any backdrop. Default is #ffffff. Do not mention background in the style or subject descriptions."

Previous value: -"Output format: png, jpg, or webp. Defaults to png."New value: +"Output format: png, jpg, or webp. Defaults to png. jpg has no alpha channel, so a transparent set is png or webp."

Previous value: -"The background color used; absent for transparent sets."New value: +"The background color used, or transparent."

Previous value: -"The generated images: subject name, filename inside the zip, and pixel width and height."New value: +"The generated images: each one's file name inside the zip, its subject, and its pixel width and height."

Added value: +{
+  "description": "The subject, variation or scene this image was made from, as the call gave it.",
+  "type": "string"
+}

Added value: +"The image's file name inside the zip."

Removed value: -{
-  "type": "string"
-}

Previous value: -[
-  "name",
-  "filename"
-]New value: +[
+  "filename",
+  "description"
+]

Previous value: -"Present only on a validation suggestion: the cleaned style text, for review. An empty string means the cleanup removed the style entirely (nothing in it was usable as a style) - replace it, or use styleReferences. Absent on refs-only requests. No generation ran and nothing was charged."New value: +"Present only on a validation suggestion: the cleaned style text, for review. An empty string means the cleanup removed the style entirely (nothing in it was usable as a style) - replace it, or use styleReferences. Absent when the style was not checked (references only, or an extension). No generation ran and nothing was charged."

Added value: +{
+  "description": "The largest base size, in pixels, at which export_set keeps every density of this batch crisp (no image enlarged past its source pixels) at its current levers; absent when no base size does. An image or character set's is set by its subject or variation count at generation, and edits to size, canvas, margin or sizing can move it; an illustration set's is a quarter of the longest side its scenes were drawn at, the largest it exports at.",
+  "type": "integer"
+}

Previous value: -"True when it can be re-delivered: a set with edit_image_set, an illustration with edit_illustration (each has a source to cut from)."New value: +"True when edit_set can re-deliver it (it has a source to cut from)."

Previous value: -"True when an edit (edit_image_set for a set, edit_illustration for an illustration) has changed its delivery from what was generated; a reset makes it false again."New value: +"True when edit_set has changed its delivery from what was generated; a reset makes it false again."

Removed value: -{
-  "description": "The largest base size, in pixels, at which export_icons keeps every density of this set crisp (no subject enlarged past its source pixels) at its current levers; absent when no base size does. Set by the subject count at generation; edits to size, canvas, margin or sizing can move it.",
-  "type": "integer"
-}

Previous value: -"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, edit_illustration, export_icons and create_reference's sourceGeneration."New value: +"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_set, export_set, extend_image_set, extend_character_set, extend_illustration_set and create_reference's sourceGeneration."

Removed value: -{
-  "additionalProperties": false,
-  "description": "The delivery settings now in force for an illustration (width, height, format, quality): the first delivery's until edit_illustration changes them.",
-  "properties": {
-    "format": {
-      "type": "string"
-    },
-    "height": {
-      "type": "integer"
-    },
-    "quality": {
-      "type": "integer"
-    },
-    "width": {
-      "type": "integer"
-    }
-  },
-  "required": [
-    "width",
-    "height",
-    "format"
-  ],
-  "type": [
-    "null",
-    "object"
-  ]
-}

Previous value: -"The delivery levers now in force for a set (width, height, canvas, minimumMargin, sizing, format, quality, background): the first delivery's until edit_image_set changes them. Absent on illustrations and on sets from before editing existed."New value: +"The delivery levers now in force (width, height, canvas, minimumMargin, sizing, format, quality, background; an illustration set has width, height, format and quality): the first delivery's until edit_set changes them. Absent on sets from before editing existed."

Previous value: -"integer"New value: +[
+  "null",
+  "integer"
+]

Previous value: -[
-  "minimumMargin",
-  "format"
-]New value: +[
+  "format"
+]

Previous value: -"The canvas this set would be delivered on at native size (its trimmed frame plus margin): the size any re-delivery compares against. For an illustration, the size the model made it at, the largest it can be delivered at."New value: +"The canvas this set would be delivered on at native size, with no width or height fixed: the size any re-delivery compares against. For an illustration set, the size the model draws its scenes at, the largest they can be delivered at."

Previous value: -"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (a set's style, subjects and references; an illustration's prompt and references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, format, quality, background) are the current delivery, which an edit rewrites (edit_image_set for a set, edit_illustration for an illustration's width, height, format and quality), so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its shape follows the tool named in its own tool field. Sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background for solid-background sets, and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places. Illustrations carry prompt, references as zip-relative paths when the call used them, width, height, format, quality and filename. Read subjects[].description to reproduce a set: a subject given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."New value: +"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (the style or character, the list and the references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, sizing, format, quality) are the current delivery, which edit_set rewrites, so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its background is the color the set was generated on, or transparent (an edit that composes a transparent set over a color leaves it transparent here; levers holds the color). Its shape follows the tool named in its own tool field. Image sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background (a color, or transparent), and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places; illustration sets carry style, styleReferences, scenes, width, height, format and quality. Read each entry's description (subjects[], variations[] or scenes[]) to reproduce a set: an entry given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."

Previous value: -"Where each reference image this generation was made with came from, in call order: the generation and delivered image it was copied from (what create_reference takes as sourceGeneration and sourceImage), or uploaded for a hand-uploaded file. The same images are inside promptJSON as zip-relative paths, under styleReferences, characterReferences or references, by tool. Absent when none were used."New value: +"Where each reference image this generation was made with came from, in call order: the generation and delivered image it was copied from (what create_reference takes as sourceGeneration and sourceImage), or uploaded for a hand-uploaded file. The same images are inside promptJSON as zip-relative paths, under styleReferences or characterReferences, by tool. Absent when none were used."

Added value: +{
+  "description": "The largest base size, in pixels, at which export_set keeps every density of this batch crisp; absent when no base size does.",
+  "type": "integer"
+}

Previous value: -"True when it can be re-delivered: a set with edit_image_set, an illustration with edit_illustration (each has a source to cut from)."New value: +"True when edit_set can re-deliver it (it has a source to cut from)."

Previous value: -"True when an edit (edit_image_set for a set, edit_illustration for an illustration) has changed its delivery from what was generated."New value: +"True when edit_set has changed its delivery from what was generated."

Removed value: -{
-  "description": "The largest base size, in pixels, at which export_icons keeps every density of this set crisp; absent when no base size does.",
-  "type": "integer"
-}

Previous value: -"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, edit_illustration, export_icons and create_reference's sourceGeneration."New value: +"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_set, export_set, extend_image_set, extend_character_set, extend_illustration_set and create_reference's sourceGeneration."

Removed value: -{
-  "description": "An illustration's prompt, as written; absent for sets.",
-  "type": "string"
-}

Previous value: -"The style a set was generated with, as written; absent for illustrations and for sets styled by reference images alone."New value: +"The style a set was generated with, as written; absent for character sets and for sets styled by reference images alone."

Previous value: -"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"the fox waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."

Previous value: -"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"the fox waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."

Previous value: -"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"the fox waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."New value: +"What the character is doing in each image, one entry per image: either a list of descriptions or objects with description and filename (e.g. [{\"description\": \"waving hello\", \"filename\": \"waving.png\"}]). Each entry is one isolated variation of the same character - its pose, action, expression, how strongly it feels it, and anything it holds or wears - not a scene or setting. Entries must be distinct: entries differing only in case, punctuation, or spacing are rejected as the same. Text can use only letters, numbers, dashes, spaces, and apostrophes, and must start and end with a letter or number."

Previous value: -"Ids of the generations whose delivered images seeded this one's style references - the set lineage. Absent when this generation extended nothing."New value: +"Ids of the generations whose delivered images seeded this one's references - the set lineage. Absent when this generation extended nothing."

Added value: +{
+  "description": "Where each reference image this generation was made with came from, in call order: the generation and delivered image it was copied from (what create_reference takes as sourceGeneration and sourceImage), or uploaded for a hand-uploaded file. The same images are inside promptJSON as zip-relative paths, under styleReferences, characterReferences or references, by tool. Absent when none were used.",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "from": {
+        "description": "The generation id this reference image came from; accepted by create_reference's sourceGeneration.",
+        "type": "string"
+      },
+      "image": {
+        "description": "The delivered image filename inside that generation; accepted by create_reference's sourceImage.",
+        "type": "string"
+      },
+      "uploaded": {
+        "description": "True for a hand-uploaded reference that came from no generation.",
+        "type": "boolean"
+      }
+    },
+    "type": "object"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

Removed value: -{
-  "description": "The style references this generation was made with, in call order, each identified by the delivered image it came from when known, and reusable via create_reference. Distinct from promptJSON.styleReferences, which records the same references as zip-relative paths inside the original call. Absent when no references were used.",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "from": {
-        "description": "The generation id this reference image came from; accepted by create_reference's sourceGeneration.",
-        "type": "string"
-      },
-      "image": {
-        "description": "The delivered image filename inside that generation; accepted by create_reference's sourceImage.",
-        "type": "string"
-      },
-      "uploaded": {
-        "description": "True for a hand-uploaded reference that came from no generation.",
-        "type": "boolean"
-      }
-    },
-    "type": "object"
-  },
-  "type": [
-    "null",
-    "array"
-  ]
-}

Previous value: -"Ids of the generations whose delivered images seeded this one's style references: the set lineage, for gathering a whole set's ids."New value: +"Ids of the generations whose delivered images seeded this one's references: the set lineage, for gathering a whole set's ids."

Added value: +{
+  "description": "Up to 3 reference images for the illustration: a style to match, or a character, product or place to include. Each entry is a ref_ token from the create_reference tool: create an upload slot, send the image file with the curl command it returns, then pass the token here. Image data itself never goes in a tool call; ref_ tokens are the only accepted form. Uploads take PNG, JPEG, or WebP; size and dimension limits are given in the create_reference tool's description. The prompt is used as written, so say in it what each image is for, in the order given (e.g. 'in the style of the first image, the dog from the second image asleep on a sofa'). How closely the result follows a reference is up to the model.",
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

Previous value: -"When the current delivery was cut: the generation time, or the time of the last edit_image_set."New value: +"When the current delivery was cut: the generation time, or the time of the last edit."

Previous value: -"True when this set can be re-delivered with edit_image_set (it has a source to cut from)."New value: +"True when it can be re-delivered: a set with edit_image_set, an illustration with edit_illustration (each has a source to cut from)."

Previous value: -"True when edit_image_set has changed this set's delivery from what was generated; a reset makes it false again."New value: +"True when an edit (edit_image_set for a set, edit_illustration for an illustration) has changed its delivery from what was generated; a reset makes it false again."

Previous value: -"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, export_icons and create_reference's sourceGeneration."New value: +"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, edit_illustration, export_icons and create_reference's sourceGeneration."

Added value: +{
+  "additionalProperties": false,
+  "description": "The delivery settings now in force for an illustration (width, height, format, quality): the first delivery's until edit_illustration changes them.",
+  "properties": {
+    "format": {
+      "type": "string"
+    },
+    "height": {
+      "type": "integer"
+    },
+    "quality": {
+      "type": "integer"
+    },
+    "width": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "width",
+    "height",
+    "format"
+  ],
+  "type": [
+    "null",
+    "object"
+  ]
+}

Previous value: -"The canvas this set would be delivered on at native size (its trimmed frame plus margin): the size any re-delivery compares against."New value: +"The canvas this set would be delivered on at native size (its trimmed frame plus margin): the size any re-delivery compares against. For an illustration, the size the model made it at, the largest it can be delivered at."

Previous value: -"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. Its style, subjects and styleReferences are the original call and no edit can change them; its delivery levers (width, height, canvas, minimumMargin, format, quality, background) are the batch's current delivery, which edit_image_set rewrites, so reusing this reproduces the set as it stands now rather than as first delivered. The edited flag says whether that has happened. Its shape follows the tool named in its own tool field. Sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background for solid-background sets, and styleReferences as zip-relative paths when the call used them. Illustrations carry prompt, width, height, format, quality and filename. Read subjects[].description to reproduce a set: a subject given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."New value: +"The batch's own prompt.json, verbatim - the same bytes that ship inside the zip. What it asked for (a set's style, subjects and references; an illustration's prompt and references) is the original call, and no edit can change it; its delivery settings (width, height, canvas, minimumMargin, format, quality, background) are the current delivery, which an edit rewrites (edit_image_set for a set, edit_illustration for an illustration's width, height, format and quality), so reusing this reproduces the generation as it stands now rather than as first delivered. The edited flag says whether that has happened. Its shape follows the tool named in its own tool field. Sets carry style, subjects as {description, filename} pairs, format, quality, minimumMargin, validation, width and height when an axis was fixed, background for solid-background sets, and styleReferences as zip-relative paths when the call used them; character sets carry character, variations and characterReferences in those places. Illustrations carry prompt, references as zip-relative paths when the call used them, width, height, format, quality and filename. Read subjects[].description to reproduce a set: a subject given in object form has a description that differs from its filename, so search.webp may have been asked for as a magnifying glass."

Previous value: -"When the current delivery was cut: the generation time, or the time of the last edit_image_set."New value: +"When the current delivery was cut: the generation time, or the time of the last edit."

Previous value: -"True when this set can be re-delivered with edit_image_set (it has a source to cut from)."New value: +"True when it can be re-delivered: a set with edit_image_set, an illustration with edit_illustration (each has a source to cut from)."

Previous value: -"True when edit_image_set has changed this set's delivery from what was generated."New value: +"True when an edit (edit_image_set for a set, edit_illustration for an illustration) has changed its delivery from what was generated."

Previous value: -"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, export_icons and create_reference's sourceGeneration."New value: +"The generation's id: the random segment of its download URLs, accepted by get_generations, delete_generations, edit_image_set, edit_illustration, export_icons and create_reference's sourceGeneration."

Previous value: -"Visual style for all images, e.g. flat minimalist, hand-drawn sketch, 3D glossy, pixel art. Text that does not describe a visual style is rejected. Provide this, styleReferences, or both - together they hold a style most tightly (the text pins the style, the references show it applied), which is the recommended way to extend an existing set across multiple calls."New value: +"Visual style for all images, e.g. flat minimalist, hand-drawn sketch, 3D glossy, pixel art. Text that does not describe a visual style is rejected. Provide this, styleReferences, or both - together they hold a style most tightly (the text pins the style, the references show it applied)."

Previous value: -"Up to 3 reference images that define the style, alone or alongside the style parameter (with both, the text pins the style and the references show it applied - the tightest hold, recommended when extending an existing set). Each entry is a ref_ token from the create_reference tool: create an upload slot, send the image file with the curl command it returns, then pass the token here. Image data itself never goes in a tool call; ref_ tokens are the only accepted form. Uploads take PNG, JPEG, or WebP; size and dimension limits are given in the create_reference tool's description, and oversized images are rejected with a clear message - larger reference images do not improve results. The images are used as style guides only: their rendering technique carries over, their subjects do not appear in the output. Provide at least one of style and styleReferences."New value: +"Up to 3 reference images that define the style, alone or alongside the style parameter (with both, the text pins the style and the references show it applied - the tightest hold). Each entry is a ref_ token from the create_reference tool: create an upload slot, send the image file with the curl command it returns, then pass the token here. Image data itself never goes in a tool call; ref_ tokens are the only accepted form. Uploads take PNG, JPEG, or WebP; size and dimension limits are given in the create_reference tool's description, and oversized images are rejected with a clear message - larger reference images do not improve results. The images are used as style guides only: their rendering technique carries over, their subjects do not appear in the output. Provide at least one of style and styleReferences."

Removed value: -"The style the set was generated with."

Previous value: -"Visual style for all images, e.g. flat minimalist, hand-drawn sketch, 3D glossy, pixel art. Text that does not describe a visual style is rejected. Provide this, styleReferences, or both - together they hold a style most tightly (the text pins the style, the references show it applied), which is the recommended way to extend an existing set across multiple calls."New value: +"Visual style for all images, e.g. flat minimalist, hand-drawn sketch, 3D glossy, pixel art. Text that does not describe a visual style is rejected. Provide this, styleReferences, or both - together they hold a style most tightly (the text pins the style, the references show it applied)."

Previous value: -"Up to 3 reference images that define the style, alone or alongside the style parameter (with both, the text pins the style and the references show it applied - the tightest hold, recommended when extending an existing set). Each entry is a ref_ token from the create_reference tool: create an upload slot, send the image file with the curl command it returns, then pass the token here. Image data itself never goes in a tool call; ref_ tokens are the only accepted form. Uploads take PNG, JPEG, or WebP; size and dimension limits are given in the create_reference tool's description, and oversized images are rejected with a clear message - larger reference images do not improve results. The images are used as style guides only: their rendering technique carries over, their subjects do not appear in the output. Provide at least one of style and styleReferences."New value: +"Up to 3 reference images that define the style, alone or alongside the style parameter (with both, the text pins the style and the references show it applied - the tightest hold). Each entry is a ref_ token from the create_reference tool: create an upload slot, send the image file with the curl command it returns, then pass the token here. Image data itself never goes in a tool call; ref_ tokens are the only accepted form. Uploads take PNG, JPEG, or WebP; size and dimension limits are given in the create_reference tool's description, and oversized images are rejected with a clear message - larger reference images do not improve results. The images are used as style guides only: their rendering technique carries over, their subjects do not appear in the output. Provide at least one of style and styleReferences."

Previous value: -"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size (relative sizing scales nothing but a subject far larger than the rest, fill scales each subject to its frame). The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs."New value: +"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size (relative sizing scales nothing but a subject far larger than the rest, fill scales each subject to its frame) - the highest detail, though dimensions then vary between generations. The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs. A fixed size guarantees consistent dimensions across images and generations but applies Lanczos resampling which may soften fine detail; if the user will post-process the images, recommend leaving both unset."

Removed value: -"The style the set was generated with."

Added value: +{
+  "description": "The character text a character set was generated with, as written; absent for other tools and for character sets made from references alone.",
+  "type": "string"
+}

Previous value: -"New format: png, webp, or jpg. Left out, the current format stays. jpg has no alpha: on a transparent set it composes the images over white unless a background color is given in the same call."New value: +"New format: png, webp, or jpg. Left out, the current format stays. jpg has no alpha: on a transparent set it composes the images over white unless a background color is in force (given in the same call or kept from an earlier edit)."

Previous value: -"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size with no scaling or distortion - the highest detail, though dimensions then vary between generations. The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs. A fixed size guarantees consistent dimensions across images and generations but applies Lanczos resampling which may soften fine detail; if the user will post-process the images, recommend leaving both unset."New value: +"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size (relative sizing scales nothing but a subject far larger than the rest, fill scales each subject to its frame) - the highest detail, though dimensions then vary between generations. The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs. A fixed size guarantees consistent dimensions across images and generations but applies Lanczos resampling which may soften fine detail; if the user will post-process the images, recommend leaving both unset."

Previous value: -"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size with no scaling or distortion. The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs."New value: +"Delivered width in pixels. Give both width and height for an exact box (every image lands on it, one uniform scale, the shorter axis padded); give only one and the other axis hugs each subject at that scale plus the margin (so images in the set differ on it); give neither and images arrive at their native size (relative sizing scales nothing but a subject far larger than the rest, fill scales each subject to its frame). The per-axis range is given in the tool description; a given axis outside it is rejected, and the hugging axis is whatever each subject needs."

Previous value: -"The largest base size, in pixels, at which export_icons keeps every density of this set crisp (no subject enlarged past its source pixels) at its current levers; absent when no base size does. Fixed by the subject count at generation; edits to margin or sizing move it."New value: +"The largest base size, in pixels, at which export_icons keeps every density of this set crisp (no subject enlarged past its source pixels) at its current levers; absent when no base size does. Set by the subject count at generation; edits to size, canvas, margin or sizing can move it."

Added value: +{
+  "description": "The image's height in pixels.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image's width in pixels.",
+  "type": "integer"
+}

Previous value: -"The generated images: subject name and filename inside the zip."New value: +"The generated images: subject name, filename inside the zip, and pixel width and height."

Added value: +{
+  "description": "The image's height in pixels.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image's width in pixels.",
+  "type": "integer"
+}

Previous value: -"The generated images: subject name and filename inside the zip."New value: +"The generated images: subject name, filename inside the zip, and pixel width and height."

Added value: +{
+  "description": "The image's height in pixels.",
+  "type": "integer"
+}

Added value: +{
+  "description": "The image's width in pixels.",
+  "type": "integer"
+}

Previous value: -trueNew value: +{
+  "anyOf": [
+    {
+      "title": "Subject name",
+      "type": "string"
+    },
+    {
+      "properties": {
+        "description": {
+          "description": "The subject to draw.",
+          "type": "string"
+        },
+        "filename": {
+          "description": "Optional name for the delivered file (e.g. overview.webp); without it the name comes from the description.",
+          "type": "string"
+        }
+      },
+      "title": "Subject with filename",
+      "type": "object"
+    }
+  ]
+}

Previous value: -trueNew value: +{
+  "anyOf": [
+    {
+      "title": "Subject name",
+      "type": "string"
+    },
+    {
+      "properties": {
+        "description": {
+          "description": "The subject to draw.",
+          "type": "string"
+        },
+        "filename": {
+          "description": "Optional name for the delivered file (e.g. overview.webp); without it the name comes from the description.",
+          "type": "string"
+        }
+      },
+      "title": "Subject with filename",
+      "type": "object"
+    }
+  ]
+}