--- title: MiniMax H3 Image Highspeed | Runware Docs url: https://runware.ai/docs/models/minimax-h3-image-highspeed description: Faster H3 Image generation and multi-reference editing at up to 20 megapixels --- # MiniMax H3 Image Highspeed ![MiniMax H3 Image Highspeed](https://assets.runware.ai/covers/minimax-h3-image-highspeed.jpg) MiniMax H3 Image Highspeed is the faster variant of MiniMax H3 Image, with the same parameters, limits and output sizes. It creates images from text or edits and combines up to 16 reference images, at 1K, 2K or 4K, or at a custom width and height up to 20 megapixels. It suits interactive tools, high-volume pipelines and iterative editing where turnaround matters. - **Status**: live - **ID**: `minimax:h3@image-highspeed` - Try in Playground - **Creator**: MiniMax - **Release Date**: November 10, 2026 - **Capabilities**: Text to Image, Image to Image, Edit, Checkpoint ## Pricing ~$0.0573 typical run **Rates** (per 1M tokens) - Text input: `$2.30` - Image input: `$3.00` - Image output: `$7.60` **4 example generations** - [text-to-image](https://runware.ai/docs/models/minimax-h3-image-highspeed/examples#example-botanical-garden-picture-book-spread): `$0.0418` (~15s) - [text-to-image](https://runware.ai/docs/models/minimax-h3-image-highspeed/examples#example-mycelium-materials-magazine-cover): `$0.0422` (~13s) - [reference-to-image](https://runware.ai/docs/models/minimax-h3-image-highspeed/examples#example-pneumatic-mail-history-book-cover): `$0.0725` (~20s) - [reference-to-image](https://runware.ai/docs/models/minimax-h3-image-highspeed/examples#example-historic-storefront-restoration-visualization): `$0.0743` (~21s) billed per token, so a request costs what the model produced · times vary, measured end to end · [How pricing works](https://runware.ai/docs/models-api/pricing) ## Compatibility & Validation When `inputs.referenceImages` is provided, `settings.promptOptimizer` must be `true`. --- `resolution` cannot be used with `width/height`. --- `width` and `height` must be used together. --- When none of `width` and `height` are provided, `settings.promptOptimizer` must be `true`. ## Notes **Variant of H3 Image:** takes the same parameters and limits as `minimax:h3@image` and uses the same number of tokens per request. Its image tokens are billed at a higher rate in exchange for faster generation. **Modes:** a prompt alone generates an image. Adding `inputs.referenceImages` switches to editing, where the prompt refers to each reference by its position (image 1, image 2) and can give each one a role, such as the product from one image and the color palette from another. **Prompt optimizer:** `settings.promptOptimizer` rewrites the prompt into a detailed scene description before generating, and editing always uses it. With it off, the prompt is used as written and the model reads only about its first 4,096 tokens. **Size:** with `resolution`, the model sets the width and height itself, following the references or a ratio it picks from the prompt. With no size at all, the output is 4K. An exact `width` and `height` is generated as given, never scaled or rounded. **Pricing:** billed per token. An output of up to about 4 megapixels uses about 4,100 image tokens, so 1K and 2K cost about the same, and 4K uses about 16,400. The rewritten prompt counts as text input, and each reference image adds about 2,050 input tokens. ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `imageInference` Identifier for the type of task being performed. ### [taskUUID](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [outputType](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-outputtype) - **Type**: `string` - **Default**: `URL` Image output type. **Allowed values**: `URL` `base64Data` `dataURI` ### [outputFormat](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-outputformat) - **Type**: `string` - **Default**: `JPG` Specifies the file format of the generated output. The available values depend on the task type and the specific model's capabilities. - \`JPG\`: Best for photorealistic images with smaller file sizes (no transparency). - \`PNG\`: Lossless compression, supports high quality and transparency (alpha channel). - \`WEBP\`: Modern format providing superior compression and transparency support. > [!NOTE] > \*\*Transparency\*\*: If you are using features like background removal or LayerDiffuse that require transparency, you must select a format that supports an alpha channel (e.g., \`PNG\`, \`WEBP\`, \`TIFF\`). \`JPG\` does not support transparency. **Allowed values**: `JPG` `PNG` `WEBP` ### [outputQuality](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-outputquality) - **Type**: `integer` - **Min**: `20` - **Max**: `99` - **Default**: `95` Compression quality of the output. Higher values preserve quality but increase file size. ### [webhookURL](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-webhookurl) - **Type**: `string` - **Format**: `uri` Webhook URL that receives JSON responses via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available. **Learn more** (1 resource): - [Webhooks](https://runware.ai/docs/models-api/webhooks) (platform) ### [deliveryMethod](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-deliverymethod) - **Type**: `string` - **Default**: `sync` Determines how the API delivers task results. **Allowed values**: - `sync` Returns results directly in the API response. Over HTTP, a task still running after 120 seconds continues as an async task and comes back with status 'processing'. Poll for its results using getResponse. - `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. **Learn more** (1 resource): - [Task Polling](https://runware.ai/docs/models-api/task-polling) (platform) ### [uploadEndpoint](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-uploadendpoint) - **Type**: `string` - **Format**: `uri` Specifies a URL where the generated content will be automatically uploaded using the HTTP PUT method. The raw binary data of the media file is sent directly as the request body. For secure uploads to cloud storage, use presigned URLs that include temporary authentication credentials. **Common use cases:** - **Cloud storage**: Upload directly to S3 buckets, Google Cloud Storage, or Azure Blob Storage using presigned URLs. - **CDN integration**: Upload to content delivery networks for immediate distribution. ```text // S3 presigned URL for secure upload https://your-bucket.s3.amazonaws.com/generated/content.mp4?X-Amz-Signature=abc123&X-Amz-Expires=3600 // Google Cloud Storage presigned URL https://storage.googleapis.com/your-bucket/content.jpg?X-Goog-Signature=xyz789 // Custom storage endpoint https://storage.example.com/uploads/generated-image.jpg ``` The content data will be sent as the request body to the specified URL when generation is complete. ### [safety](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-safety) - **Path**: `safety.checkContent` - **Type**: `object (1 property)` Content safety checking configuration for image generation. #### [checkContent](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-safety-checkcontent) - **Path**: `safety.checkContent` - **Type**: `boolean` Enable or disable content safety checking. Increases total generation time. ### [ttl](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-ttl) - **Type**: `integer` - **Min**: `60` Time-to-live (TTL) in seconds for generated content. Only applies when `outputType` is `URL`. ### [includeCost](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-includecost) - **Type**: `boolean` Include task cost in the response. ### [numberResults](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-numberresults) - **Type**: `integer` - **Min**: `1` - **Max**: `20` - **Default**: `1` Number of results to generate. Each result uses a different seed, producing variations of the same parameters. **Inputs** Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object. ### [referenceImages](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-inputs-referenceimages) - **Path**: `inputs.referenceImages` - **Type**: `array of strings` - **Min items**: `1` - **Max items**: `16` - **Size (each)**: `128 px to 8192 px` - **Aspect ratio (each)**: `1:4 to 4:1` - **File size (each)**: `up to 64 MB` List of reference images (UUID, URL, Data URI, or Base64). **Core Parameters** Primary parameters that define the task output. ### [model](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-model) - **Type**: `string` - **Required**: true - **Value**: `minimax:h3@image-highspeed` Send `auto` instead of an AIR identifier to have the model router choose the model for this task. The rest of the request is unchanged, every value you send is kept, and only the parameters you leave out are filled in. See [Model Router](https://runware.ai/docs/models-api/model-router). **Learn more** (3 resources): - [Text To Image: Model Selection](https://runware.ai/docs/learn/text-to-image#model-selection) (learn) - [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/learn/image-inpainting#model-specialized-inpainting-models) (learn) - [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/learn/image-outpainting#other-critical-parameters) (learn) ### [positivePrompt](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-positiveprompt) - **Type**: `string` - **Required**: true - **Min**: `1` - **Max**: `32000` Text prompt describing elements to include in the generated output. **Learn more** (1 resource): - [Prompts](https://runware.ai/docs/learn/prompts) (learn) ### [width](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-width) - **Type**: `integer` - **Min**: `468` - **Max**: `7745` Width of the generated media in pixels. **Learn more** (2 resources): - [Dimensions](https://runware.ai/docs/learn/dimensions) (learn) - [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn) ### [height](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-height) - **Type**: `integer` - **Min**: `468` - **Max**: `7745` Height of the generated media in pixels. **Learn more** (2 resources): - [Dimensions](https://runware.ai/docs/learn/dimensions) (learn) - [Image Outpainting: Dimensions Critical For Outpainting](https://runware.ai/docs/learn/image-outpainting#dimensions-critical-for-outpainting) (learn) ### [resolution](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-resolution) - **Type**: `string` Resolution preset for the output. When used with input media, automatically matches the aspect ratio from the input. Without reference images, the model picks the aspect ratio from the prompt. **Allowed values**: `1K` `2K` `4K` **Settings** Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object. ### [promptOptimizer](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-settings-promptoptimizer) - **Path**: `settings.promptOptimizer` - **Type**: `boolean` - **Default**: `true` Automatic prompt optimization. Affects reproducibility. **Features** Standalone addons and post-processing features. ### [watermark](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark) - **Path**: `advancedFeatures.watermark` - **Type**: `object (6 properties)` Configuration object for adding watermarks to generated videos. Watermarks can be applied using either text or image content with customizable positioning and appearance. You must provide either `text` or `image` content for the watermark, but not both. **Text watermark**: ```json "advancedFeatures": { "watermark": { "text": "© 2025 Company", "displayPosition": "bottom-right", "opacity": 0.6, "fontColor": "#ffffff", "bgColor": "#000000" } } ``` **Image watermark**: ```json "advancedFeatures": { "watermark": { "image": "c64351d5-4c59-42f7-95e1-eace013eddab", "displayPosition": "top-left", "opacity": 0.6 } } ``` **Tiled watermark**: ```json "advancedFeatures": { "watermark": { "text": "PREVIEW", "tiled": true, "opacity": 0.4, "fontColor": "#cccccc" } } ``` #### [text](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-text) - **Path**: `advancedFeatures.watermark.text` - **Type**: `string` - **Min**: `2` - **Max**: `32` Watermark text. #### [image](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-image) - **Path**: `advancedFeatures.watermark.image` - **Type**: `string` Watermark image (UUID, URL, Data URI, or Base64). #### [displayPosition](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-displayposition) - **Path**: `advancedFeatures.watermark.displayPosition` - **Type**: `string` Watermark position. **Allowed values**: `top-left` `top-center` `top-right` `center-left` `center-center` `center-right` `bottom-left` `bottom-center` `bottom-right` `tiled` #### [opacity](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-opacity) - **Path**: `advancedFeatures.watermark.opacity` - **Type**: `float` - **Min**: `0.1` - **Max**: `1` - **Step**: `0.01` Watermark opacity. #### [fontColor](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-fontcolor) - **Path**: `advancedFeatures.watermark.fontColor` - **Type**: `string` Text color in hex format. #### [bgColor](https://runware.ai/docs/models/minimax-h3-image-highspeed#request-advancedfeatures-watermark-bgcolor) - **Path**: `advancedFeatures.watermark.bgColor` - **Type**: `string` Background color in hex format. ## Response Parameters ### [taskType](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `imageInference` Identifier for the type of task this response belongs to. ### [taskUUID](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier echoed from the original request, used to match async responses to their tasks. ### [imageUUID](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-imageuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the output image. ### [imageURL](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-imageurl) - **Type**: `string` - **Format**: `uri` URL of the output image. ### [imageBase64Data](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-imagebase64data) - **Type**: `string` Base64-encoded image data. ### [imageDataURI](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-imagedatauri) - **Type**: `string` - **Format**: `uri` Data URI of the output image. ### [seed](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-seed) - **Type**: `integer` The seed used for generation. If none was provided, shows the randomly generated seed. ### [NSFWContent](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-nsfwcontent) - **Type**: `boolean` Flag indicating if NSFW content was detected. ### [cost](https://runware.ai/docs/models/minimax-h3-image-highspeed#response-cost) - **Type**: `float` Task cost in USD. Present when `includeCost` is set to `true` in the request. ## Examples ### text-to-image (text-to-image) ![Mycelium Materials Magazine Cover](https://assets.runware.ai/examples/minimax-h3-image-highspeed/219b89e6-723e-43d3-b883-9aebf34da91d.jpg) ```json { "taskType": "imageInference", "taskUUID": "6b467bc8-27d7-45a4-bb12-af59a551355c", "model": "minimax:h3@image-highspeed", "positivePrompt": "Create a finished landscape digital magazine cover about mycelium-based architecture, shown straight-on as the artwork itself with no mockup, device, border, or surrounding scene. Editorial layout: place the large masthead \"MATTER GROWN\" across the upper left, set in bold condensed uppercase sans serif letters; directly below it, place the smaller issue line \"ISSUE 08 — MYCELIUM\". Use the main headline \"BUILDINGS THAT BREATHE\" in two large stacked lines at the lower left. Beneath it, add the small deck \"Inside the race to turn fungi into structural materials\". Place \"FIELD NOTES / 2027\" in tiny uppercase type at the upper right. Render only these exact words, with clean spelling and no additional text.\n\nThe cover image is a precise overhead editorial still life on a warm off-white laboratory table. Arrange exactly six mycelium construction samples in an orderly loose grid across the center and right side: one tall cream ribbed brick at top center, one circular porous tile at top right, one rust-red compressed panel at middle center, one pale beige arch-shaped block at middle right, one charcoal-gray acoustic wedge at bottom center, and one small branching white fungal composite at bottom right. Keep the lower-left area visually quiet behind the headline. Add a thin cobalt-blue ruler, a stainless steel caliper, and several restrained specimen-label lines without readable microtext. The materials should look physically credible, tactile, fibrous, dry, and engineered rather than like food.\n\nArt direction: contemporary European architecture journal, rigorous Swiss editorial grid softened by organic materials. Palette of bone white, mushroom beige, rust, charcoal, and vivid cobalt blue. Crisp top-down studio photography, soft directional daylight from upper left, subtle contact shadows, fine surface detail, premium matte-print character, generous negative space, intelligent and optimistic mood. Strong hierarchy and highly legible typography, balanced for a 3:2 landscape cover.", "width": 1536, "height": 1024 } ``` --- ### text-to-image (text-to-image) ![Botanical Garden Picture-Book Spread](https://assets.runware.ai/examples/minimax-h3-image-highspeed/7914299f-37b3-4201-96ca-86c44b1d62eb.jpg) ```json { "taskType": "imageInference", "taskUUID": "e3453bf8-d62a-4be1-9939-a287b4c7a41b", "model": "minimax:h3@image-highspeed", "positivePrompt": "Create a finished landscape children’s nonfiction picture-book spread about lesser long-nosed bats pollinating agave flowers at night. Design it as one continuous 3:2 illustration spanning two facing pages, with a subtle vertical safe gutter through the center and no book mockup, page edges, interface, or border.\n\nLAYOUT AND CONTENT: Place the headline “THE NIGHT GARDENERS” in the upper-left quadrant, arranged on two lines in very large, bold, hand-cut uppercase lettering. Place the sentence “Eight bats carry tomorrow’s desert in their fur.” in a small cream narration box at the lower left, set in clear, friendly dark-blue lettering. Reproduce both quoted texts exactly, with correct spelling and punctuation. Include no other words, letters, labels, numbers, signatures, or logos.\n\nShow exactly eight bats, all clearly separate and countable: one large foreground bat at lower right approaching a luminous agave bloom; two medium bats feeding from separate flower clusters around the central agave stalk; one medium bat banking above the left-page agave rosette; three small flying bats spaced across the upper sky; and one small bat silhouetted against the full moon at upper right. Do not add any additional bats, partial bats, or bat-like shapes.\n\nThe central subject is a towering flowering agave with pale blossoms crossing the spread while keeping its main stalk slightly right of the gutter. Surround it with low desert plants, prickly pear, rocks, and distant mesas. Show tiny golden pollen grains dusting the muzzles and fur of the three feeding bats, making the pollination story immediately understandable. Preserve open sky behind the title and keep all important faces and text away from the center gutter.\n\nART DIRECTION: sophisticated cut-paper and gouache illustration for ages 6–9, with simplified geometric silhouettes, tactile deckled edges, subtle dry-brush texture, and crisp editorial composition. Limited nocturnal palette of deep indigo, moonlit turquoise, dusty coral, magenta cactus fruit, warm cream, and pollen gold. Gentle moonlight creates luminous flower tips and readable bat silhouettes. Curious, calm, and wondrous rather than spooky; scientifically grounded anatomy with charming expressive poses. Print-ready picture-book quality, strong visual hierarchy, clean typography, no photorealism, no gradients that look digital, no extra decorative text.", "width": 1536, "height": 1024 } ``` --- ### reference-to-image (reference-to-image) ![Historic Storefront Restoration Visualization](https://assets.runware.ai/examples/minimax-h3-image-highspeed/0e25331a-0ed8-4684-b64b-6301c52c4ba8.jpg) ```json { "taskType": "imageInference", "taskUUID": "661f20be-9d0b-4a14-ad7f-8e6aea8425d1", "model": "minimax:h3@image-highspeed", "positivePrompt": "Create a finished 2K landscape architectural restoration visualization for a historic-preservation architect. Use image 1 as the primary contemporary site photograph and preserve its exact camera position, perspective, crop, facade proportions, roofline, brick massing, three-window arrangement, party-wall relationships, sidewalk geometry, neighboring building fragments, and soft overcast lighting unchanged. Use image 2 strictly as the historical evidence reference for the restoration design: accurately reconstruct its original cast-iron storefront columns, divided-light display windows, glazed recessed entrance, prism-glass transom, pressed-metal cornice, traditional wood trim profiles, masonry joint character, and striped canvas awning on the building in image 1. Do not copy image 2's monochrome treatment, photographic damage, people, street objects, or old camera distortion.\n\nShow the facade as carefully restored rather than newly built: gently cleaned warm red brick with subtle age variation, compatible buff lime-mortar repointing, repaired dark bronze-green painted cast iron, deep charcoal wood storefront framing, clear glazing with faint reflections, slightly irregular historic glass, and a muted cream-and-umber awning. Retain believable minor patina and hand-crafted irregularities. Remove plywood, temporary patches, loose cables, and obvious modern deterioration while preserving sound historic fabric. Keep the horizontal signboard blank, with no invented business name, labels, captions, logos, border, split-screen treatment, presentation-board graphics, or UI. Photorealistic preservation rendering, measured and credible material detailing, restrained natural color, diffuse cloudy daylight, documentary architectural photography, sharp facade detail without exaggerated HDR, no people, no cars, no construction equipment.", "resolution": "2K", "inputs": { "referenceImages": [ "https://assets.runware.ai/assets/inputs/3e4e538b-6998-47e7-ab76-cc749b426209.jpg", "https://assets.runware.ai/assets/inputs/76bdd0d1-cbe4-457e-8148-66fee863b158.jpg" ] } } ``` --- ### reference-to-image (reference-to-image) ![Pneumatic Mail History Book Cover](https://assets.runware.ai/examples/minimax-h3-image-highspeed/15f70cf1-4315-4780-be11-97626ad5d985.jpg) ```json { "taskType": "imageInference", "taskUUID": "b2219c64-7f7b-49c8-a316-92d9647a2c0d", "model": "minimax:h3@image-highspeed", "positivePrompt": "Create a finished portrait-format front cover for an authoritative university-press history book about the forgotten pneumatic postal networks beneath modern cities. Use both supplied references together. Image 1 provides the hero object: preserve the pneumatic mail capsule’s exact cylindrical silhouette, proportions, ribbed cap construction, scratches, dents, tarnished brass patina and dark seams unchanged. Do not redesign, simplify, duplicate or add branding to the capsule. Enlarge it into a bold diagonal foreground element rising from lower left toward upper right, photographed with convincing dimensionality. Image 2 provides the setting, perspective and color language: preserve the tunnel’s recognizable structural layout, central vanishing point, tiled walls, parallel pipe positions, maintenance walkway, aged cream, soot black, rust red and tungsten amber palette unchanged. Integrate the capsule naturally over this setting while retaining the tunnel architecture.\n\nArt direction: sophisticated archival photomontage combining 1930s transport graphics with disciplined contemporary Swiss editorial design. Intelligent, kinetic and historical rather than nostalgic or steampunk. Use hard geometric cropping, subtle halftone grain, fine registration texture and restrained paper tactility while keeping the capsule and tunnel photographically credible. Strong depth leads toward the distant utility light. High contrast with generous controlled negative space in the upper third for typography.\n\nSet clear, correctly spelled cover typography as an intentional part of the design. Large condensed sans-serif uppercase title on separate lines: “THE CITY” then “IN TUBES”. Add the smaller subtitle: “How Pneumatic Post Moved the Modern Metropolis”. Place the author name at the bottom: “DR. LEONORA VOSS”. Typography should be cream and rust red with excellent hierarchy and legibility, aligned to a strict modernist grid without covering the capsule’s cap or the tunnel vanishing point. No additional copy, badges, logos or decorative pseudo-writing. Deliver only the flat, edge-to-edge front cover artwork, not a physical book mockup, not a dust jacket spread, no spine, no back cover, no hands, no shelves and no surrounding environment.", "resolution": "2K", "inputs": { "referenceImages": [ "https://assets.runware.ai/assets/inputs/226a5527-e977-4317-b843-98ff88ca445d.jpg", "https://assets.runware.ai/assets/inputs/ee84fb09-dd45-4e95-938a-58b817cb909c.jpg" ] } } ```