{
  "schemaVersion": "1.0",
  "item": {
    "slug": "vgl",
    "name": "Visual Gen Ai Language",
    "source": "tencent",
    "type": "skill",
    "category": "AI 智能",
    "sourceUrl": "https://clawhub.ai/galbria/vgl",
    "canonicalUrl": "https://clawhub.ai/galbria/vgl",
    "targetPlatform": "OpenClaw"
  },
  "install": {
    "downloadMode": "redirect",
    "downloadUrl": "/downloads/vgl",
    "sourceDownloadUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=vgl",
    "sourcePlatform": "tencent",
    "targetPlatform": "OpenClaw",
    "installMethod": "Manual import",
    "extraction": "Extract archive",
    "prerequisites": [
      "OpenClaw"
    ],
    "packageFormat": "ZIP package",
    "includedAssets": [
      "SKILL.md",
      "references/schema-reference.md"
    ],
    "primaryDoc": "SKILL.md",
    "quickSetup": [
      "Download the package from Yavira.",
      "Extract the archive and review SKILL.md first.",
      "Import or place the package into your OpenClaw setup."
    ],
    "agentAssist": {
      "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
      "steps": [
        "Download the package from Yavira.",
        "Extract it into a folder your agent can access.",
        "Paste one of the prompts below and point your agent at the extracted folder."
      ],
      "prompts": [
        {
          "label": "New install",
          "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
        },
        {
          "label": "Upgrade existing",
          "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
        }
      ]
    },
    "sourceHealth": {
      "source": "tencent",
      "status": "healthy",
      "reason": "direct_download_ok",
      "recommendedAction": "download",
      "checkedAt": "2026-04-30T16:55:25.780Z",
      "expiresAt": "2026-05-07T16:55:25.780Z",
      "httpStatus": 200,
      "finalUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
      "contentType": "application/zip",
      "probeMethod": "head",
      "details": {
        "probeUrl": "https://wry-manatee-359.convex.site/api/v1/download?slug=network",
        "contentDisposition": "attachment; filename=\"network-1.0.0.zip\"",
        "redirectLocation": null,
        "bodySnippet": null
      },
      "scope": "source",
      "summary": "Source download looks usable.",
      "detail": "Yavira can redirect you to the upstream package for this source.",
      "primaryActionLabel": "Download for OpenClaw",
      "primaryActionHref": "/downloads/vgl"
    },
    "validation": {
      "installChecklist": [
        "Use the Yavira download entry.",
        "Review SKILL.md after the package is downloaded.",
        "Confirm the extracted package contains the expected setup assets."
      ],
      "postInstallChecks": [
        "Confirm the extracted package includes the expected docs or setup files.",
        "Validate the skill or prompts are available in your target agent workspace.",
        "Capture any manual follow-up steps the agent could not complete."
      ]
    },
    "downloadPageUrl": "https://openagent3.xyz/downloads/vgl",
    "agentPageUrl": "https://openagent3.xyz/skills/vgl/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vgl/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vgl/agent.md"
  },
  "agentAssist": {
    "summary": "Hand the extracted package to your coding agent with a concrete install brief instead of figuring it out manually.",
    "steps": [
      "Download the package from Yavira.",
      "Extract it into a folder your agent can access.",
      "Paste one of the prompts below and point your agent at the extracted folder."
    ],
    "prompts": [
      {
        "label": "New install",
        "body": "I downloaded a skill package from Yavira. Read SKILL.md from the extracted folder and install it by following the included instructions. Tell me what you changed and call out any manual steps you could not complete."
      },
      {
        "label": "Upgrade existing",
        "body": "I downloaded an updated skill package from Yavira. Read SKILL.md from the extracted folder, compare it with my current installation, and upgrade it while preserving any custom configuration unless the package docs explicitly say otherwise. Summarize what changed and any follow-up checks I should run."
      }
    ]
  },
  "documentation": {
    "source": "clawhub",
    "primaryDoc": "SKILL.md",
    "sections": [
      {
        "title": "Bria VGL — Full Control Over Image Generation",
        "body": "Define every visual attribute as structured JSON instead of hoping natural language gets it right. VGL (Visual Generation Language) gives you explicit, deterministic control over objects, lighting, camera settings, composition, and style for Bria's FIBO models.\n\nRelated Skill: Use bria-ai to execute these VGL prompts via the Bria API. VGL defines the structured control format; bria-ai handles generation, editing, and background removal."
      },
      {
        "title": "Core Concept",
        "body": "VGL replaces ambiguous natural language prompts with deterministic JSON that explicitly declares every visual attribute: objects, lighting, camera settings, composition, and style. This ensures reproducible, controllable image generation."
      },
      {
        "title": "Operation Modes",
        "body": "ModeInputOutputUse CaseGenerateText promptVGL JSONCreate new image from descriptionEditImage + instructionVGL JSONModify reference imageEdit_with_MaskMasked image + instructionVGL JSONFill grey masked regionsCaptionImage onlyVGL JSONDescribe existing imageRefineExisting JSON + editUpdated VGL JSONModify existing prompt"
      },
      {
        "title": "JSON Schema",
        "body": "Output a single valid JSON object with these required keys:"
      },
      {
        "title": "1. short_description (String)",
        "body": "Concise summary of image content, max 200 words. Include key subjects, actions, setting, and mood."
      },
      {
        "title": "2. objects (Array, max 5 items)",
        "body": "Each object requires:\n\n{\n  \"description\": \"Detailed description, max 100 words\",\n  \"location\": \"center | top-left | bottom-right foreground | etc.\",\n  \"relative_size\": \"small | medium | large within frame\",\n  \"shape_and_color\": \"Basic shape and dominant color\",\n  \"texture\": \"smooth | rough | metallic | furry | fabric | etc.\",\n  \"appearance_details\": \"Notable visual details\",\n  \"relationship\": \"Relationship to other objects\",\n  \"orientation\": \"upright | tilted 45 degrees | facing left | horizontal | etc.\"\n}\n\nHuman subjects add:\n\n{\n  \"pose\": \"Body position description\",\n  \"expression\": \"winking | joyful | serious | surprised | calm\",\n  \"clothing\": \"Attire description\",\n  \"action\": \"What the person is doing\",\n  \"gender\": \"Gender description\",\n  \"skin_tone_and_texture\": \"Skin appearance\"\n}\n\nObject clusters add:\n\n{\n  \"number_of_objects\": 3\n}\n\nSize guidance: If a person is the main subject, use \"medium-to-large\" or \"large within frame\"."
      },
      {
        "title": "3. background_setting (String)",
        "body": "Overall environment, setting, and background elements not in objects."
      },
      {
        "title": "4. lighting (Object)",
        "body": "{\n  \"conditions\": \"bright daylight | dim indoor | studio lighting | golden hour | blue hour | overcast\",\n  \"direction\": \"front-lit | backlit | side-lit from left | top-down\",\n  \"shadows\": \"long, soft shadows | sharp, defined shadows | minimal shadows\"\n}"
      },
      {
        "title": "5. aesthetics (Object)",
        "body": "{\n  \"composition\": \"rule of thirds | symmetrical | centered | leading lines | medium shot | close-up\",\n  \"color_scheme\": \"monochromatic blue | warm complementary | high contrast | pastel\",\n  \"mood_atmosphere\": \"serene | energetic | mysterious | joyful | dramatic | peaceful\"\n}\n\nFor people as main subject, specify shot type in composition: \"medium shot\", \"close-up\", \"portrait composition\"."
      },
      {
        "title": "6. photographic_characteristics (Object)",
        "body": "{\n  \"depth_of_field\": \"shallow | deep | bokeh background\",\n  \"focus\": \"sharp focus on subject | soft focus | motion blur\",\n  \"camera_angle\": \"eye-level | low angle | high angle | dutch angle | bird's-eye\",\n  \"lens_focal_length\": \"wide-angle | 50mm standard | 85mm portrait | telephoto | macro\"\n}\n\nFor people: Prefer \"standard lens (35mm-50mm)\" or \"portrait lens (50mm-85mm)\". Avoid wide-angle unless specified."
      },
      {
        "title": "7. style_medium (String)",
        "body": "\"photograph\" | \"oil painting\" | \"watercolor\" | \"3D render\" | \"digital illustration\" | \"pencil sketch\"\n\nDefault to \"photograph\" unless explicitly requested otherwise."
      },
      {
        "title": "8. artistic_style (String)",
        "body": "If not photograph, describe characteristics in max 3 words: \"impressionistic, vibrant, textured\"\n\nFor photographs, use \"realistic\" or similar."
      },
      {
        "title": "9. context (String)",
        "body": "Describe the image type/purpose:\n\n\"High-fashion editorial photograph for magazine spread\"\n\"Concept art for fantasy video game\"\n\"Commercial product photography for e-commerce\""
      },
      {
        "title": "10. text_render (Array)",
        "body": "Default: empty array []\n\nOnly populate if user explicitly provides exact text content:\n\n{\n  \"text\": \"Exact text from user (never placeholder)\",\n  \"location\": \"center | top-left | bottom\",\n  \"size\": \"small | medium | large\",\n  \"color\": \"white | red | blue\",\n  \"font\": \"serif typeface | sans-serif | handwritten | bold impact\",\n  \"appearance_details\": \"Metallic finish | 3D effect | etc.\"\n}\n\nException: Universal text integral to objects (e.g., \"STOP\" on stop sign)."
      },
      {
        "title": "11. edit_instruction (String)",
        "body": "Single imperative command describing the edit/generation."
      },
      {
        "title": "For Standard Edits (no mask)",
        "body": "Start with action verb, describe changes, never reference \"original image\":\n\nCategoryRewritten InstructionStyle changeTurn the image into the cartoon style.Object attributeChange the dog's color to black and white.Add elementAdd a wide-brimmed felt hat to the subject.Remove objectRemove the book from the subject's hands.Replace objectChange the rose to a bright yellow sunflower.LightingChange the lighting from dark and moody to bright and vibrant.CompositionChange the perspective to a wider shot.Text changeChange the text \"Happy Anniversary\" to \"Hello\".QualityRefine the image to obtain increased clarity and sharpness."
      },
      {
        "title": "For Masked Region Edits",
        "body": "Reference \"masked regions\" or \"masked area\" as target:\n\nIntentRewritten InstructionObject generationGenerate a white rose with a blue center in the masked region.ExtensionExtend the image into the masked region to create a scene featuring...Background fillCreate the following background in the masked region: A vast ocean extending to horizon.Atmospheric fillFill the background masked area with a clear, bright blue sky with wispy clouds.Subject restorationRestore the area in the mask with a young woman.Environment infillCreate inside the masked area: a greenhouse with rows of plants under glass ceiling."
      },
      {
        "title": "Standard Edit Mode",
        "body": "Preserve ALL visual properties unless explicitly changed by instruction:\n\nSubject identity, pose, appearance\nObject existence, location, size, orientation\nComposition, camera angle, lens characteristics\nStyle/medium\n\nOnly change what the edit strictly requires."
      },
      {
        "title": "Masked Edit Mode",
        "body": "Preserve all visible (non-masked) portions exactly\nFill grey masked regions to blend seamlessly with unmasked areas\nMatch existing style, lighting, and subject matter\nNever describe grey masks—describe content that fills them"
      },
      {
        "title": "Example Output",
        "body": "{\n  \"short_description\": \"A professional businesswoman in a navy blazer stands confidently in a modern glass office, holding a tablet. Natural daylight streams through floor-to-ceiling windows, creating a warm, productive atmosphere.\",\n  \"objects\": [\n    {\n      \"description\": \"A confident businesswoman in her 30s with shoulder-length dark hair, wearing a tailored navy blazer over a white blouse. She holds a tablet in her left hand while gesturing naturally with her right.\",\n      \"location\": \"center-right\",\n      \"relative_size\": \"large within frame\",\n      \"shape_and_color\": \"Human figure, navy and white clothing\",\n      \"texture\": \"smooth fabric, professional attire\",\n      \"appearance_details\": \"Minimal jewelry, well-groomed professional appearance\",\n      \"relationship\": \"Main subject, interacting with tablet\",\n      \"orientation\": \"facing slightly left, three-quarter view\",\n      \"pose\": \"Standing upright, relaxed professional stance\",\n      \"expression\": \"confident, approachable smile\",\n      \"clothing\": \"Tailored navy blazer, white silk blouse, dark trousers\",\n      \"action\": \"Presenting or reviewing information on tablet\",\n      \"gender\": \"female\",\n      \"skin_tone_and_texture\": \"Medium warm skin tone, healthy smooth complexion\"\n    },\n    {\n      \"description\": \"A modern tablet device with a bright display showing charts and graphs\",\n      \"location\": \"center, held by subject\",\n      \"relative_size\": \"small\",\n      \"shape_and_color\": \"Rectangular, silver frame with illuminated screen\",\n      \"texture\": \"smooth glass and metal\",\n      \"appearance_details\": \"Thin profile, business application visible on screen\",\n      \"relationship\": \"Held by businesswoman, focus of her attention\",\n      \"orientation\": \"vertical, screen facing viewer at slight angle\",\n      \"pose\": null,\n      \"expression\": null,\n      \"clothing\": null,\n      \"action\": null,\n      \"gender\": null,\n      \"skin_tone_and_texture\": null,\n      \"number_of_objects\": null\n    }\n  ],\n  \"background_setting\": \"Modern corporate office interior with floor-to-ceiling windows overlooking a city skyline. Minimalist furniture in neutral tones, potted plants adding touches of green.\",\n  \"lighting\": {\n    \"conditions\": \"bright natural daylight\",\n    \"direction\": \"side-lit from left through windows\",\n    \"shadows\": \"soft, natural shadows\"\n  },\n  \"aesthetics\": {\n    \"composition\": \"rule of thirds, medium shot\",\n    \"color_scheme\": \"professional blues and neutral whites with warm accents\",\n    \"mood_atmosphere\": \"confident, professional, welcoming\"\n  },\n  \"photographic_characteristics\": {\n    \"depth_of_field\": \"shallow, background slightly soft\",\n    \"focus\": \"sharp focus on subject's face and upper body\",\n    \"camera_angle\": \"eye-level\",\n    \"lens_focal_length\": \"portrait lens (85mm)\"\n  },\n  \"style_medium\": \"photograph\",\n  \"artistic_style\": \"realistic\",\n  \"context\": \"Corporate portrait photography for company website or LinkedIn professional profile.\",\n  \"text_render\": [],\n  \"edit_instruction\": \"Generate a professional businesswoman in a modern office environment holding a tablet.\"\n}"
      },
      {
        "title": "Common Pitfalls",
        "body": "Don't invent text - Keep text_render empty unless user provides exact text\nDon't over-describe - Max 5 objects, prioritize most important\nMatch the mode - Use correct edit_instruction format for masked vs standard edits\nPreserve fidelity - Only change what's explicitly requested\nBe specific - Use concrete values (\"85mm portrait lens\") not vague terms (\"nice camera\")\nNull for irrelevant - Human-specific fields should be null for non-human objects"
      },
      {
        "title": "curl Example",
        "body": "curl -X POST \"https://engine.prod.bria-api.com/v2/image/generate\" \\\n  -H \"api_token: $BRIA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"structured_prompt\": \"{\\\"short_description\\\": \\\"...\\\", ...}\",\n    \"prompt\": \"Generate this scene\",\n    \"aspect_ratio\": \"16:9\"\n  }'"
      },
      {
        "title": "References",
        "body": "Schema Reference - Complete JSON schema with all parameter values\nbria-ai - API client and endpoint documentation for executing VGL prompts"
      }
    ],
    "body": "Bria VGL — Full Control Over Image Generation\n\nDefine every visual attribute as structured JSON instead of hoping natural language gets it right. VGL (Visual Generation Language) gives you explicit, deterministic control over objects, lighting, camera settings, composition, and style for Bria's FIBO models.\n\nRelated Skill: Use bria-ai to execute these VGL prompts via the Bria API. VGL defines the structured control format; bria-ai handles generation, editing, and background removal.\n\nCore Concept\n\nVGL replaces ambiguous natural language prompts with deterministic JSON that explicitly declares every visual attribute: objects, lighting, camera settings, composition, and style. This ensures reproducible, controllable image generation.\n\nOperation Modes\nMode\tInput\tOutput\tUse Case\nGenerate\tText prompt\tVGL JSON\tCreate new image from description\nEdit\tImage + instruction\tVGL JSON\tModify reference image\nEdit_with_Mask\tMasked image + instruction\tVGL JSON\tFill grey masked regions\nCaption\tImage only\tVGL JSON\tDescribe existing image\nRefine\tExisting JSON + edit\tUpdated VGL JSON\tModify existing prompt\nJSON Schema\n\nOutput a single valid JSON object with these required keys:\n\n1. short_description (String)\n\nConcise summary of image content, max 200 words. Include key subjects, actions, setting, and mood.\n\n2. objects (Array, max 5 items)\n\nEach object requires:\n\n{\n  \"description\": \"Detailed description, max 100 words\",\n  \"location\": \"center | top-left | bottom-right foreground | etc.\",\n  \"relative_size\": \"small | medium | large within frame\",\n  \"shape_and_color\": \"Basic shape and dominant color\",\n  \"texture\": \"smooth | rough | metallic | furry | fabric | etc.\",\n  \"appearance_details\": \"Notable visual details\",\n  \"relationship\": \"Relationship to other objects\",\n  \"orientation\": \"upright | tilted 45 degrees | facing left | horizontal | etc.\"\n}\n\n\nHuman subjects add:\n\n{\n  \"pose\": \"Body position description\",\n  \"expression\": \"winking | joyful | serious | surprised | calm\",\n  \"clothing\": \"Attire description\",\n  \"action\": \"What the person is doing\",\n  \"gender\": \"Gender description\",\n  \"skin_tone_and_texture\": \"Skin appearance\"\n}\n\n\nObject clusters add:\n\n{\n  \"number_of_objects\": 3\n}\n\n\nSize guidance: If a person is the main subject, use \"medium-to-large\" or \"large within frame\".\n\n3. background_setting (String)\n\nOverall environment, setting, and background elements not in objects.\n\n4. lighting (Object)\n{\n  \"conditions\": \"bright daylight | dim indoor | studio lighting | golden hour | blue hour | overcast\",\n  \"direction\": \"front-lit | backlit | side-lit from left | top-down\",\n  \"shadows\": \"long, soft shadows | sharp, defined shadows | minimal shadows\"\n}\n\n5. aesthetics (Object)\n{\n  \"composition\": \"rule of thirds | symmetrical | centered | leading lines | medium shot | close-up\",\n  \"color_scheme\": \"monochromatic blue | warm complementary | high contrast | pastel\",\n  \"mood_atmosphere\": \"serene | energetic | mysterious | joyful | dramatic | peaceful\"\n}\n\n\nFor people as main subject, specify shot type in composition: \"medium shot\", \"close-up\", \"portrait composition\".\n\n6. photographic_characteristics (Object)\n{\n  \"depth_of_field\": \"shallow | deep | bokeh background\",\n  \"focus\": \"sharp focus on subject | soft focus | motion blur\",\n  \"camera_angle\": \"eye-level | low angle | high angle | dutch angle | bird's-eye\",\n  \"lens_focal_length\": \"wide-angle | 50mm standard | 85mm portrait | telephoto | macro\"\n}\n\n\nFor people: Prefer \"standard lens (35mm-50mm)\" or \"portrait lens (50mm-85mm)\". Avoid wide-angle unless specified.\n\n7. style_medium (String)\n\n\"photograph\" | \"oil painting\" | \"watercolor\" | \"3D render\" | \"digital illustration\" | \"pencil sketch\"\n\nDefault to \"photograph\" unless explicitly requested otherwise.\n\n8. artistic_style (String)\n\nIf not photograph, describe characteristics in max 3 words: \"impressionistic, vibrant, textured\"\n\nFor photographs, use \"realistic\" or similar.\n\n9. context (String)\n\nDescribe the image type/purpose:\n\n\"High-fashion editorial photograph for magazine spread\"\n\"Concept art for fantasy video game\"\n\"Commercial product photography for e-commerce\"\n10. text_render (Array)\n\nDefault: empty array []\n\nOnly populate if user explicitly provides exact text content:\n\n{\n  \"text\": \"Exact text from user (never placeholder)\",\n  \"location\": \"center | top-left | bottom\",\n  \"size\": \"small | medium | large\",\n  \"color\": \"white | red | blue\",\n  \"font\": \"serif typeface | sans-serif | handwritten | bold impact\",\n  \"appearance_details\": \"Metallic finish | 3D effect | etc.\"\n}\n\n\nException: Universal text integral to objects (e.g., \"STOP\" on stop sign).\n\n11. edit_instruction (String)\n\nSingle imperative command describing the edit/generation.\n\nEdit Instruction Formats\nFor Standard Edits (no mask)\n\nStart with action verb, describe changes, never reference \"original image\":\n\nCategory\tRewritten Instruction\nStyle change\tTurn the image into the cartoon style.\nObject attribute\tChange the dog's color to black and white.\nAdd element\tAdd a wide-brimmed felt hat to the subject.\nRemove object\tRemove the book from the subject's hands.\nReplace object\tChange the rose to a bright yellow sunflower.\nLighting\tChange the lighting from dark and moody to bright and vibrant.\nComposition\tChange the perspective to a wider shot.\nText change\tChange the text \"Happy Anniversary\" to \"Hello\".\nQuality\tRefine the image to obtain increased clarity and sharpness.\nFor Masked Region Edits\n\nReference \"masked regions\" or \"masked area\" as target:\n\nIntent\tRewritten Instruction\nObject generation\tGenerate a white rose with a blue center in the masked region.\nExtension\tExtend the image into the masked region to create a scene featuring...\nBackground fill\tCreate the following background in the masked region: A vast ocean extending to horizon.\nAtmospheric fill\tFill the background masked area with a clear, bright blue sky with wispy clouds.\nSubject restoration\tRestore the area in the mask with a young woman.\nEnvironment infill\tCreate inside the masked area: a greenhouse with rows of plants under glass ceiling.\nFidelity Rules\nStandard Edit Mode\n\nPreserve ALL visual properties unless explicitly changed by instruction:\n\nSubject identity, pose, appearance\nObject existence, location, size, orientation\nComposition, camera angle, lens characteristics\nStyle/medium\n\nOnly change what the edit strictly requires.\n\nMasked Edit Mode\nPreserve all visible (non-masked) portions exactly\nFill grey masked regions to blend seamlessly with unmasked areas\nMatch existing style, lighting, and subject matter\nNever describe grey masks—describe content that fills them\nExample Output\n{\n  \"short_description\": \"A professional businesswoman in a navy blazer stands confidently in a modern glass office, holding a tablet. Natural daylight streams through floor-to-ceiling windows, creating a warm, productive atmosphere.\",\n  \"objects\": [\n    {\n      \"description\": \"A confident businesswoman in her 30s with shoulder-length dark hair, wearing a tailored navy blazer over a white blouse. She holds a tablet in her left hand while gesturing naturally with her right.\",\n      \"location\": \"center-right\",\n      \"relative_size\": \"large within frame\",\n      \"shape_and_color\": \"Human figure, navy and white clothing\",\n      \"texture\": \"smooth fabric, professional attire\",\n      \"appearance_details\": \"Minimal jewelry, well-groomed professional appearance\",\n      \"relationship\": \"Main subject, interacting with tablet\",\n      \"orientation\": \"facing slightly left, three-quarter view\",\n      \"pose\": \"Standing upright, relaxed professional stance\",\n      \"expression\": \"confident, approachable smile\",\n      \"clothing\": \"Tailored navy blazer, white silk blouse, dark trousers\",\n      \"action\": \"Presenting or reviewing information on tablet\",\n      \"gender\": \"female\",\n      \"skin_tone_and_texture\": \"Medium warm skin tone, healthy smooth complexion\"\n    },\n    {\n      \"description\": \"A modern tablet device with a bright display showing charts and graphs\",\n      \"location\": \"center, held by subject\",\n      \"relative_size\": \"small\",\n      \"shape_and_color\": \"Rectangular, silver frame with illuminated screen\",\n      \"texture\": \"smooth glass and metal\",\n      \"appearance_details\": \"Thin profile, business application visible on screen\",\n      \"relationship\": \"Held by businesswoman, focus of her attention\",\n      \"orientation\": \"vertical, screen facing viewer at slight angle\",\n      \"pose\": null,\n      \"expression\": null,\n      \"clothing\": null,\n      \"action\": null,\n      \"gender\": null,\n      \"skin_tone_and_texture\": null,\n      \"number_of_objects\": null\n    }\n  ],\n  \"background_setting\": \"Modern corporate office interior with floor-to-ceiling windows overlooking a city skyline. Minimalist furniture in neutral tones, potted plants adding touches of green.\",\n  \"lighting\": {\n    \"conditions\": \"bright natural daylight\",\n    \"direction\": \"side-lit from left through windows\",\n    \"shadows\": \"soft, natural shadows\"\n  },\n  \"aesthetics\": {\n    \"composition\": \"rule of thirds, medium shot\",\n    \"color_scheme\": \"professional blues and neutral whites with warm accents\",\n    \"mood_atmosphere\": \"confident, professional, welcoming\"\n  },\n  \"photographic_characteristics\": {\n    \"depth_of_field\": \"shallow, background slightly soft\",\n    \"focus\": \"sharp focus on subject's face and upper body\",\n    \"camera_angle\": \"eye-level\",\n    \"lens_focal_length\": \"portrait lens (85mm)\"\n  },\n  \"style_medium\": \"photograph\",\n  \"artistic_style\": \"realistic\",\n  \"context\": \"Corporate portrait photography for company website or LinkedIn professional profile.\",\n  \"text_render\": [],\n  \"edit_instruction\": \"Generate a professional businesswoman in a modern office environment holding a tablet.\"\n}\n\nCommon Pitfalls\nDon't invent text - Keep text_render empty unless user provides exact text\nDon't over-describe - Max 5 objects, prioritize most important\nMatch the mode - Use correct edit_instruction format for masked vs standard edits\nPreserve fidelity - Only change what's explicitly requested\nBe specific - Use concrete values (\"85mm portrait lens\") not vague terms (\"nice camera\")\nNull for irrelevant - Human-specific fields should be null for non-human objects\ncurl Example\ncurl -X POST \"https://engine.prod.bria-api.com/v2/image/generate\" \\\n  -H \"api_token: $BRIA_API_KEY\" \\\n  -H \"Content-Type: application/json\" \\\n  -d '{\n    \"structured_prompt\": \"{\\\"short_description\\\": \\\"...\\\", ...}\",\n    \"prompt\": \"Generate this scene\",\n    \"aspect_ratio\": \"16:9\"\n  }'\n\nReferences\nSchema Reference - Complete JSON schema with all parameter values\nbria-ai - API client and endpoint documentation for executing VGL prompts"
  },
  "trust": {
    "sourceLabel": "tencent",
    "provenanceUrl": "https://clawhub.ai/galbria/vgl",
    "publisherUrl": "https://clawhub.ai/galbria/vgl",
    "owner": "galbria",
    "version": "1.2.1",
    "license": null,
    "verificationStatus": "Indexed source record"
  },
  "links": {
    "detailUrl": "https://openagent3.xyz/skills/vgl",
    "downloadUrl": "https://openagent3.xyz/downloads/vgl",
    "agentUrl": "https://openagent3.xyz/skills/vgl/agent",
    "manifestUrl": "https://openagent3.xyz/skills/vgl/agent.json",
    "briefUrl": "https://openagent3.xyz/skills/vgl/agent.md"
  }
}