Technical Specifications of `runwayml-text-to-image`

Specification	Details
Model ID on CometAPI	`runwayml-text-to-image`
Upstream provider	Runway
Primary capability	Text-to-image generation for creating AI-generated still images from natural-language prompts.
Closest official Runway model family	Runway’s image-generation API offering, centered on `gen4_image` and related image models. CometAPI exposes this through the platform identifier `runwayml-text-to-image`.
Input types	Text prompts, and in Runway’s broader image API stack, optional image references for multimodal image generation/editing workflows.
Output type	Generated image.
Access method	API-based access through Runway’s developer platform and compatible integrations.
Authentication	API key / API secret-based authentication in the Runway developer setup flow.
SDK availability	Official SDK support is available for Node.js and Python-oriented workflows via Runway’s SDK resources.
Pricing context	Runway lists image-generation pricing for `gen4_image` at 5 credits per 720p image or 8 credits per 1080p image; `gen4_image_turbo` is listed at 2 credits per image. Exact CometAPI billing may differ by platform.
Typical use cases	Marketing visuals, concept art, storyboards, product mockups, design ideation, and other creative image-generation tasks. This is an inference based on Runway’s stated image-generation positioning.

What is `runwayml-text-to-image`?

runwayml-text-to-image is CometAPI’s platform identifier for accessing Runway-powered text-to-image generation. Based on Runway’s official API documentation and product materials, the underlying capability is designed to turn natural-language prompts into generated images, with Runway’s current API model lineup including dedicated image models such as gen4_image and gen4_image_turbo.

In practice, this model category is intended for developers and product teams that want to embed high-quality image creation into applications, internal tools, creative workflows, or user-facing experiences. Runway positions its API as a developer platform for integrating generative media into apps and products, and its image API supports both prompt-based generation and, in some cases, reference-guided workflows for more controlled outputs.

Because CometAPI uses its own normalized model ID format, you should keep using runwayml-text-to-image when calling the model through CometAPI, even though Runway’s native documentation refers to specific upstream model names such as gen4_image.

Main features of `runwayml-text-to-image`

Text-to-image generation: Converts plain-language prompts into AI-generated images suitable for creative, visual, and product-oriented workflows.
Runway image-model backing: The capability aligns with Runway’s dedicated image-generation stack, especially gen4_image, which is presented as Runway’s flagship image model in its API model catalog.
Reference-aware workflows: Runway’s image API documentation highlights support for text-plus-image reference patterns, enabling more control over composition, style, or subject guidance where supported by the upstream model.
Developer-friendly API access: Runway provides a documented API, setup guides, and SDKs intended to simplify integration into production applications.
Multiple quality/cost options: Runway publishes separate image models with different pricing profiles, including gen4_image and gen4_image_turbo, which suggests flexibility between output quality and generation cost.
Creative production use: The model is well suited to ideation, asset generation, visual prototyping, concept exploration, and design assistance. This use-case framing is inferred from Runway’s product positioning around image generation for apps and creative teams.

How to access and integrate `runwayml-text-to-image`

Sign up for CometAPI and create an API key from the dashboard. Store the key securely in your environment variables or secret manager before making production requests.

Step 2: Send Requests to `runwayml-text-to-image` API

Use Runway's official API format via CometAPI. The endpoint is POST /runwayml/v1/text_to_image. Include the X-Runway-Version header.

curl https://api.cometapi.com/runwayml/v1/text_to_image \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $COMETAPI_API_KEY" \
  -H "X-Runway-Version: 2024-11-06" \
  -d '{
    "model": "gen4_aleph",
    "promptText": "Your prompt here."
  }'

Step 3: Retrieve and Verify Results