MODEL ID runware:glm-image@0

api-only

GLM-Image

by Z.ai January 14, 2026

GLM-Image is an open-source image generation model that combines an autoregressive image-token generator with a diffusion decoder to produce high-fidelity results with strong prompt adherence. It is especially strong at accurate text rendering inside images and knowledge-intensive compositions, and it supports image-to-image generation for instruction-driven edits within a single unified model.

API Options

Platform-level options for task execution and delivery.

taskType string required value: imageInference: Identifier for the type of task being performed

taskUUID string required UUID v4: UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task.

outputType string default: URL: Image output type.

Allowed values 3 values

outputFormat 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.

**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 3 values

outputQuality integer min: 20 max: 99 default: 95: Compression quality of the output. Higher values preserve quality but increase file size.

webhookURL string URI

Specifies a webhook URL where JSON responses will be sent 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
PLATFORM

deliveryMethod string default: sync

Determines how the API delivers task results.

Allowed values 2 values

: Returns complete results directly in the API response.
: Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse.

Learn more 1 resource

Task Polling
PLATFORM

uploadEndpoint string 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.

// 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 object

Content safety checking configuration for image generation.

Properties 2 properties

safety » checkContent checkContent boolean default: false: Enable or disable content safety checking. When enabled, defaults to fast mode.

safety » mode mode string default: none

Safety checking mode for image generation.

Allowed values 2 values

: Disables checking.
: Performs a single check.

ttl integer min: 60: Time-to-live (TTL) in seconds for generated content. Only applies when outputType is URL.

includeCost boolean default: false: Include task cost in the response.

numberResults 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.

inputs » referenceImages referenceImages array of strings items: 1: List of reference images (UUID, URL, Data URI, or Base64).

Generation Parameters

Core parameters for controlling the generated content.

model string required value: runware:glm-image@0

Identifier of the model to use for generation.

Learn more 3 resources

positivePrompt string required min: 2 max: 3000

Text prompt describing elements to include in the generated output.

Learn more 2 resources

width integer required min: 128 max: 2048 default: 1024

Width of the generated media in pixels.

Learn more 2 resources

height integer required min: 128 max: 2048 default: 1024

Height of the generated media in pixels.

Learn more 2 resources

seed integer min: 0 max: 9223372036854776000

Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range.

Learn more 1 resource

Text To Image: Seed Controlling Randomness Deterministically
GUIDE

steps integer min: 1 max: 999 default: 100

Total number of denoising steps. Higher values generally produce more detailed results but take longer.

Learn more 1 resource

Text To Image: Steps Trading Quality For Speed
GUIDE

CFGScale float min: 1 max: 30 step: 0.01 default: 10

Guidance scale representing how closely the output will resemble the prompt. Higher values produce results more aligned with the prompt.

Learn more 1 resource

Text To Image: Cfg Scale Balancing Creativity And Control
GUIDE

taskType string required value: imageInference: Type of the task.

taskUUID string required UUID v4: UUID of the task.

imageUUID string required UUID v4: UUID of the output image.

imageURL string URI: URL of the output image.

imageBase64Data string: Base64-encoded image data.

imageDataURI string URI: Data URI of the output image.

seed integer: The seed used for generation. If none was provided, shows the randomly generated seed.

NSFWContent boolean: Flag indicating if NSFW content was detected.

cost float: Task cost in USD. Present when includeCost is set to true in the request.

Text to Image

Handwritten Atlas Reading Room

Request

{
  "taskType": "imageInference",
  "taskUUID": "03ada9c5-16e0-409a-b2b7-9c77d7b51757",
  "model": "runware:glm-image@0",
  "positivePrompt": "A grand reading room inside a 19th-century geographical society, towering walnut shelves filled with atlases, suspended brass globe lamps, rolled charts, measuring tools, and a massive painted world map on the far wall. At the center, a long oak table displays open map folios, compasses, magnifiers, and labeled specimen boxes. A librarian in a deep green coat arranges documents while two travelers study routes marked in red ink. Warm amber daylight pours through tall arched windows, carrying floating dust motes and creating soft directional shadows. Include several pieces of clearly legible handwritten and engraved text in the scene: a hanging sign that reads \"Cartography Hall\", a book spine labeled \"Polar Routes 1874\", a crate tag reading \"River Survey\", and a map title saying \"Atlas of Winds\". Highly detailed, realistic textures, cinematic composition, elegant historical atmosphere, natural color palette, precise architecture, crisp focus.",
  "width": 1024,
  "height": 768,
  "seed": 45732,
  "steps": 40,
  "CFGScale": 7.5
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "03ada9c5-16e0-409a-b2b7-9c77d7b51757",
  "imageUUID": "bb7d4356-03ae-481b-b687-68f3c4f7a00f",
  "imageURL": "https://im.runware.ai/image/os/a13d12/ws/2/ii/bb7d4356-03ae-481b-b687-68f3c4f7a00f.jpg",
  "seed": 45732,
  "cost": 0.0141
}

Text to Image

Floating Archive Atrium Diorama

Request

{
  "taskType": "imageInference",
  "taskUUID": "cfa556ea-2c34-45d9-8800-487dcf83082c",
  "model": "runware:glm-image@0",
  "positivePrompt": "A richly detailed cutaway diorama of a floating public archive drifting above a patchwork floodplain at sunrise, built from weathered cedar, brass braces, glass walkways, hanging rope bridges, and suspended reading pods. Inside the multi-level atrium: librarians, cartographers, and schoolchildren studying oversized maps, seed catalogs, river specimens, and hand-labeled drawers. Accurate readable signage integrated into the scene: a carved wooden entry sign that says \"SKY TIDE ARCHIVE\", a wayfinding board with arrows labeled \"MAP ROOM\", \"SEED VAULT\", and \"UPPER STACKS\", and a small stamp on a crate reading \"DELIVER TO DELTA SCHOOL\". Outside the windows: flocks of white ibises, terraced wetlands, tiny ferries below, and distant wind pumps. Style: highly imaginative cinematic illustration with crisp focus, tactile materials, atmospheric depth, warm amber and pale turquoise palette, elegant composition, abundant micro-details, believable scale, soft sunbeams, uplifting and curious mood.",
  "width": 1024,
  "height": 768,
  "seed": 25044,
  "steps": 40,
  "CFGScale": 7.5
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "cfa556ea-2c34-45d9-8800-487dcf83082c",
  "imageUUID": "6682a474-f4a1-4ebf-8ce3-30066c62cb14",
  "imageURL": "https://im.runware.ai/image/os/a17d13/ws/2/ii/6682a474-f4a1-4ebf-8ce3-30066c62cb14.jpg",
  "seed": 25044,
  "cost": 0.0147
}

Image to Image

Riverside Herbarium Signboard Tableau

Request

{
  "taskType": "imageInference",
  "taskUUID": "2ac419c1-a561-4f61-9bb8-4c44f797ad37",
  "model": "runware:glm-image@0",
  "positivePrompt": "Transform the reference image into a highly detailed riverside herbarium display beneath a striped canvas awning on a breezy spring afternoon. Keep the tabletop arrangement recognizable, but expand it into a story-rich scene with labeled glass jars, pressed plant specimens, seed packets, handwritten botanical cards, bundles of sage and lavender, copper clips, a folded field journal, and a painted wooden sign that clearly reads 'RIVERBANK HERBARIUM'. Add a second smaller label card that clearly reads 'Specimens & Seeds'. In the background, include a calm canal, moored rowboats, willow branches, and weathered stone steps. Natural color palette, crisp textures, realistic lighting, documentary-style composition, high fidelity, precise text rendering, subtle human presence implied by recently used tools but no visible person.",
  "width": 1024,
  "height": 768,
  "seed": 16029,
  "steps": 40,
  "CFGScale": 7.5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/298877df-be25-4bd9-8813-1990e7d9e8f4.jpg"
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "2ac419c1-a561-4f61-9bb8-4c44f797ad37",
  "imageUUID": "ec273ad7-92c9-4e5f-9cb7-85c4be50fd6b",
  "imageURL": "https://im.runware.ai/image/os/a25d05/ws/2/ii/ec273ad7-92c9-4e5f-9cb7-85c4be50fd6b.jpg",
  "seed": 16029,
  "cost": 0.0397
}

Image to Image

Wayfinding Mural Transit Hall

Request

{
  "taskType": "imageInference",
  "taskUUID": "939d44af-db29-4f24-a066-183d5f52b88c",
  "model": "runware:glm-image@0",
  "positivePrompt": "Transform the reference image into a grand contemporary transit hall centered around a massive hand-painted wayfinding mural and integrated signage system. Preserve the overall architecture and camera perspective from the source image, but enrich the walls, floor accents, and overhead panels with a cohesive visual identity inspired by geology, rivers, and regional history. Include highly legible text rendered directly inside the scene: a central wall title reading \"RIVERGATE CENTRAL\", directional signs reading \"PLATFORM A\", \"PLATFORM B\", \"TICKETS\", \"EXIT\", and \"CITY TRAMS\", plus a large infographic map labeled \"REGIONAL LINES\" with small route names and icons. Add suspended colored markers, tactile floor strips, benches, subtle traveler silhouettes, and polished stone surfaces. Clean natural daylight, precise typography, balanced composition, realistic materials, sharp details, documentary architectural photography feel.",
  "width": 1024,
  "height": 768,
  "seed": 28031,
  "steps": 40,
  "CFGScale": 7.5,
  "inputs": {
    "referenceImages": [
      "https://assets.runware.ai/assets/inputs/a4b32105-2b05-4d19-a825-de1f9a816066.jpg"
    ]
  }
}

Response

{
  "taskType": "imageInference",
  "taskUUID": "939d44af-db29-4f24-a066-183d5f52b88c",
  "imageUUID": "8d4589d0-382f-4cac-bce2-2044dfaa799c",
  "imageURL": "https://im.runware.ai/image/os/a08d21/ws/2/ii/8d4589d0-382f-4cac-bce2-2044dfaa799c.jpg",
  "seed": 28031,
  "cost": 0.0378
}