bytedance/jimeng-4.6/text-to-image

POST

/openapi/v2/bytedance/jimeng-4.6/text-to-image

Jimeng Image 4.6 Text-to-Image is a high-quality image generation model from Volcengine Jimeng AI. Built on the upgraded Seedream 4.0 foundation, it generates high-resolution images from text prompts and is suitable for portraits, graphic design, creative posters, product visuals, and image stylization. Output size can be controlled with size or width/height, supporting image generation from around 1K to 4K.

Request

Authorization

Header Params

Body Params application/jsonRequired

Example

{
    "prompt": "Professional Japanese anime illustration style, full-body portrait. A stunning young anime girl with exquisitely sculpted three-dimensional facial features. She has bright and luminous eyes with vivid expressions, long and distinct eyelashes, and soft, natural facial contours. Her hair is layered and flowing, with every strand delicately rendered and showing natural luster. She wears an elaborately designed outfit featuring clear textures of fabrics, lace and bows, presenting a fresh and elegant style. The character strikes a graceful pose with perfect body proportions and gentle, lively movements. Set against a dreamy and beautiful backdrop with multi-layered soft diffused light and natural light and shadow transitions. The overall color palette is bright, soft and soothing, with sleek clean lines and smooth, full coloring. The image boasts a strong immersive atmosphere and sophisticated composition. The character wears a vivid expression, with no facial distortion or anatomical defects. The work delivers the premium visual quality of authentic anime original art.",
    "scale": 50,
    "forceSingle": false,
    "minRatio": 0.333333,
    "maxRatio": 3
}

Request Code Samples

Shell

JavaScript

Java

Swift

PHP

Python

HTTP

Objective-C

Ruby

OCaml

Dart

curl --location 'https://www.runninghub.ai/openapi/v2/bytedance/jimeng-4.6/text-to-image' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Authorization: Bearer [Your API KEY]' \
--header 'Content-Type: application/json' \
--data '{
    "prompt": "Professional Japanese anime illustration style, full-body portrait. A stunning young anime girl with exquisitely sculpted three-dimensional facial features. She has bright and luminous eyes with vivid expressions, long and distinct eyelashes, and soft, natural facial contours. Her hair is layered and flowing, with every strand delicately rendered and showing natural luster. She wears an elaborately designed outfit featuring clear textures of fabrics, lace and bows, presenting a fresh and elegant style. The character strikes a graceful pose with perfect body proportions and gentle, lively movements. Set against a dreamy and beautiful backdrop with multi-layered soft diffused light and natural light and shadow transitions. The overall color palette is bright, soft and soothing, with sleek clean lines and smooth, full coloring. The image boasts a strong immersive atmosphere and sophisticated composition. The character wears a vivid expression, with no facial distortion or anatomical defects. The work delivers the premium visual quality of authentic anime original art.",
    "scale": 50,
    "forceSingle": false,
    "minRatio": 0.333333,
    "maxRatio": 3
}'

Responses

🟢200成功

application/json

Task result query endpoint: /openapi/v2/query

Bodyapplication/json

Examples

Submit response exampleTask success response example

{
    "taskId": "2013508786110730241",
    "status": "RUNNING",
    "errorCode": "",
    "errorMessage": "",
    "results": null,
    "clientId": "f828b9af25161bc066ef152db7b29ccc",
    "promptTips": "{\"result\": true, \"error\": null, \"outputs_to_execute\": [\"4\"], \"node_errors\": {}}"
}

Modified at 2026-05-28 12:00:16

xai/rhart-imagine-image-quality/text-to-image-official-stable

wan-2.7/image-edit-pro