Skip to content
Documentation
Contact
← Back to documentation
Technical Reference

Runware

Runware.AI is a high-performance, cost-effective AI media generation API specializing in images and videos. Through this integration, workflows can automatically generate visuals via text or image prompts and interact with Runware’s full-featured API.

CategoryArtificial Intelligence
Authenticationcustom
Version0.1.7
Published scopes0 published scopes
Last updatedSeptember 30, 2026

Overview

Connect Runware with Flows360

Runware.AI is a high-performance, cost-effective AI media generation API specializing in images and videos. Through this integration, workflows can automatically generate visuals via text or image prompts and interact with Runware’s full-featured API.

Use the Runware connector to include its declared actions and events in Flows360 workflows without duplicating the integration logic inside each consuming system. This pinned connector version currently exposes 4 actions and no declared triggers.

Available actions

  • Generate Images from Text
  • Generate Images from Existing Image
  • Generate Video from Text
  • Image Background Removal

Available triggers

  • No triggers are declared in this pinned package.

The capability list above is generated from the exact reviewed connector package so the public description stays aligned with the version Flows360 operates.

Technical guide

Technical reference

Package identity

  • Connector: Runware
  • Package: @activepieces/piece-runware@0.1.7
  • Exact artifact digest: sha256:888716199249aba7cac1cd1e64ab3452170533a2267c88292d20401e5c2d5de2
  • Runtime: Activepieces-compatible deterministic worker
  • Source: the exact reviewed Activepieces source

Authentication

SECRET TEXT. Connection values are tenant-specific and remain in the consuming Studio instance; CDK stores definitions and field metadata, not customer credential values.

Action contracts

  • Generate Images from Text (generateImagesFromText), Produce images from a text description. Classification: read.
  • Generate Images from Existing Image (generateImagesFromExistingImage), Generate new images based on a provided image (image-to-image). Classification: read.
  • Generate Video from Text (generateVideoFromText), Generate video from text prompt. Classification: read.
  • Image Background Removal (imageBackgroundRemoval), Request image background removal. Classification: read.

Trigger contracts

  • No trigger delivery contracts are declared.

Verification

Runtime execution evidence is managed separately from package metadata.

Capability summary

Authenticationcustom
Supported objects4
Supported actions4
TriggersNone published

Authentication

Authentication method: custom

Authentication profiles

connection · custom
  • API Key Required · protected credential

Supported objects

ObjectReadWriteNotes
Generate Images from Text Yes No Produce images from a text description.
Generate Images from Existing Image Yes No Generate new images based on a provided image (image-to-image).
Generate Video from Text Yes No Generate video from text prompt.
Image Background Removal Yes No Request image background removal.

Supported actions

Generate Images from Text · Read

Produce images from a text description.

generate_images_from_text · Risk: low · Retry: safe

Inputs

  • model · string · Required, You can find model in the Model Explorer (https://my.runware.ai/models/all) tool.
  • positivePrompt · string · Required, A positive prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides positive guidance for the task. This parameter is essential to shape the desired results.
  • negativePrompt · string · Optional, A negative prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides negative guidance for the task. This parameter helps to avoid certain undesired results.
  • height · number · Required, Used to define the height dimension of the generated image. Certain models perform better with specific dimensions.
  • width · number · Required, Used to define the width dimension of the generated image. Certain models perform better with specific dimensions.
  • steps · number · Optional, The number of steps is the number of iterations the model will perform to generate the image. The higher the number of steps, the more detailed the image will be. However, increasing the number of steps will also increase the time it takes to generate the image and may not always result in a better image (some schedulers work differently).
  • CFGScale · number · Optional, Guidance scale represents how closely the images will resemble the prompt or how much freedom the AI model has. Higher values are closer to the prompt. Low values may reduce the quality of the results.
  • scheduler · string · Optional, An scheduler is a component that manages the inference process. Different schedulers can be used to achieve different results like more detailed images, faster inference, or more accurate results.
  • seed · number · Optional, A seed is a value used to randomize the image generation. If you want to make images reproducible (generate the same image multiple times), you can use the same seed value.
  • vae · string · Optional, VAE (Variational Autoencoder) is a type of neural network architecture used for generating images. Some models may require a specific VAE to work properly. If you want to use a specific VAE, you can provide its AIR identifier here.
  • clipSkip · number · Optional, Defines additional layer skips during prompt processing in the CLIP model. Some models already skip layers by default, this parameter adds extra skips on top of those. Different values affect how your prompt is interpreted, which can lead to variations in the generated image.
Generate Images from Existing Image · Read

Generate new images based on a provided image (image-to-image).

generate_images_from_existing_image · Risk: low · Retry: safe

Inputs

  • seedImage · string · Required, A URL for the seed image to base the generation on.
  • model · string · Required, You can find model in the Model Explorer (https://my.runware.ai/models/all) tool.
  • positivePrompt · string · Required, A positive prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides positive guidance for the task. This parameter is essential to shape the desired results.
  • height · number · Required, Used to define the height dimension of the generated image. Certain models perform better with specific dimensions.
  • width · number · Required, Used to define the width dimension of the generated image. Certain models perform better with specific dimensions.
  • negativePrompt · string · Optional, A negative prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides negative guidance for the task. This parameter helps to avoid certain undesired results.
  • strength · number · Optional, A value between 0 and 1 that indicates how much to transform the seed image. A value of 0 will keep the image as is, while a value of 1 will completely transform it according to the prompt.
  • steps · number · Optional, The number of steps is the number of iterations the model will perform to generate the image. The higher the number of steps, the more detailed the image will be. However, increasing the number of steps will also increase the time it takes to generate the image and may not always result in a better image (some schedulers work differently).
  • CFGScale · number · Optional, Guidance scale represents how closely the images will resemble the prompt or how much freedom the AI model has. Higher values are closer to the prompt. Low values may reduce the quality of the results.
  • scheduler · string · Optional, An scheduler is a component that manages the inference process. Different schedulers can be used to achieve different results like more detailed images, faster inference, or more accurate results.
Generate Video from Text · Read

Generate video from text prompt.

generate_video_from_text · Risk: low · Retry: safe

Inputs

  • positivePrompt · string · Required, A positive prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides positive guidance for the task. This parameter is essential to shape the desired results.
  • negativePrompt · string · Optional, A negative prompt is a text instruction to guide the model on generating the image. It is usually a sentence or a paragraph that provides negative guidance for the task. This parameter helps to avoid certain undesired results.
  • model · string · Required, You can find model in the Model Explorer (https://my.runware.ai/models/all) tool.
  • duration · number · Optional, The duration of the generated video in seconds.
  • fps · number · Optional, Frames per second for the generated video.
  • outputFormat · string · Optional, The format of the generated video.
  • outputQuality · number · Optional, Sets the compression quality of the output video. Higher values preserve more quality but increase file size, lower values reduce file size but decrease quality.
  • uploadEndpoint · string · Optional, 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.
  • numberResults · number · Optional, Specifies how many videos to generate for the given parameters. Each video will have the same parameters but different seeds, resulting in variations of the same concept.
Image Background Removal · Read

Request image background removal.

image_background_removal · Risk: low · Retry: safe

Inputs

  • inputImage · string · Required, A URL for the image to have its background removed.
  • model · string · Required, You can find model in the Model Explorer (https://my.runware.ai/models/all) tool.
  • outputFormat · string · Optional, The format of the output image with the background removed.
  • outputQuality · number · Optional, Sets the compression quality of the output image. Higher values preserve more quality but increase file size, lower values reduce file size but decrease quality.
  • uploadEndpoint · string · Optional, 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.

Setup

Setup

  1. Add the Runware connector to the workflow in the target Flows360 Studio instance.
  2. Create or select the tenant-specific connection required by the connector. Connection secrets remain in the Studio connection boundary and are not copied into CDK documentation.
  3. Provide the connection fields declared by the pinned package:
  • No provider credential fields are declared by the pinned package.
  1. Select the required action or trigger and complete its declared input fields. Required and optional inputs are defined by the exact package schema.
  2. Test the workflow in the appropriate environment before enabling production scheduling or event delivery.

Limitations

Limitations and operational notes

  • This content describes @activepieces/piece-runware@0.1.7; provider behaviour can change independently and should be revalidated when the provider or connector version changes.
  • Only the 4 actions and 0 triggers declared by this pinned package are represented here.
  • Tenant credentials and connection values are not stored in the public connector record.
  • Provider-side permissions, account entitlements, quotas and rate limits remain subject to the connected provider account and are not inferred when the package does not declare them.
  • Runtime execution evidence is managed separately from package metadata.

Troubleshooting

Why canu2019t the connector authenticate?

Check the tenant connection in Studio and confirm every required Runware connection field is present. Re-authorise OAuth-based connections if the provider token or consent has expired. Do not place credential values in CDK content or logs.

Why is an action or trigger unavailable?

Confirm that the workflow is using @activepieces/piece-runware@0.1.7 and compare the requested capability with the declared action and trigger list for this version. A capability that is not declared by the pinned package should not be presented as supported.

What should I check after a provider-side change?

Revalidate authentication, required fields, action/trigger behaviour and provider documentation before publishing refreshed connector content or moving a new package version into production.

github.com