DreamStudio is Stability AI's user interface for generative AI, allowing users to create and edit generated images.
DreamStudio is Stability AI's user interface for generative AI, allowing users to create and edit generated images. On Nagent, Dreamstudio is exposed as a fully-configurable artificial intelligence integration that any agent can call — 5 actions, and API key authentication. No code is required to wire Dreamstudio into your workflow — connect it once via the External Integrations panel and reuse it across every agent you build.
Agent builders use Dreamstudio to automate the kinds of tasks artificial intelligence teams previously handled manually. Concrete examples — each one is a single agent step in Nagent — include:
Every action and trigger is paired with a structured input/output schema (visible in the sections below), so when you wire Dreamstudio into Helix — our agentic agent builder — the editor knows exactly what each step expects and produces. Configure once, deploy anywhere across your Nagent agents.
Every operation an agent can call against Dreamstudio, with input parameters and output schema. Drop these into any step of an agent built in Helix.
DREAMSTUDIO_GENERATE_IMAGE_FROM_IMAGETool to generate a new image from an initial image and text prompts. Use after you have a reference image and want to transform it via text guidance.
Input parameters
Optional random seed for reproducible results
Number of diffusion steps to run
\[DEPRECATED - DO NOT USE\] Output dimensions are determined by init_image size. This parameter is ignored by the API.
\[DEPRECATED - DO NOT USE\] Output dimensions are determined by init_image size. This parameter is ignored by the API.
How many images to generate in one call
Guidance scale (how strongly to follow the prompt, 0-35)
Engine identifier for generation, e.g. 'stable-diffusion-v1-5' Validate via DREAMSTUDIO_LIST_ENGINES before calling; unsupported values cause failures.
Binary content of the input image to guide generation
List of prompt objects each with text and optional weight
Controls how much the original image is preserved (0-1). Required when init_image_mode='IMAGE_STRENGTH'.
Guidance mode for how the init_image influences the result. 'IMAGE_STRENGTH' uses image_strength, 'STEP_SCHEDULE' uses step_schedule_start/end.
Optional end fraction for image influence in the schedule (0-1). Defaults to 1.0 if omitted.
Fraction at which to start image influence in the sampling schedule (0-1). Required when init_image_mode='STEP_SCHEDULE'.
CLIP guidance presets supported by the DreamStudio image-to-image API.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DREAMSTUDIO_GENERATE_IMAGE_FROM_TEXTGenerate images from text prompts using Stability AI's text-to-image models. Use when you need to create images from textual descriptions without a reference image. Supports multiple prompts with weights, configurable dimensions, and various generation parameters.
Input parameters
Random seed for reproducible generation. Use the same seed with same parameters to get identical results. If omitted, a random seed is used.
Number of diffusion steps. More steps generally improve quality but take longer. Typical range: 30-50. If omitted, engine's default is used.
Width of generated image in pixels. Must be a multiple of 64. Constraints: For 768 engines: 589,824 ≤ height*width ≤ 1,048,576. For other engines: 262,144 ≤ height*width ≤ 1,048,576. If omitted, engine's default width is used.
Height of generated image in pixels. Must be a multiple of 64. Constraints: For 768 engines: 589,824 ≤ height*width ≤ 1,048,576. For other engines: 262,144 ≤ height*width ≤ 1,048,576. If omitted, engine's default height is used.
Available sampler algorithms for image generation.
Number of images to generate in a single request. Default is 1. Higher values consume more API credits.
Classifier-Free Guidance scale - how strictly to follow the text prompt. Higher values (7-15) follow prompt more closely, lower values (1-7) allow more creative freedom. If omitted, engine's default is used.
Engine identifier for generation (e.g., 'stable-diffusion-v1-5', 'stable-diffusion-xl-1024-v1-0'). Use DREAMSTUDIO_LIST_ENGINES to get available engines. Using invalid engine_id will cause the request to fail.
Organization ID to scope the request to. If not provided, uses the user's default organization from their account.
List of text prompts with optional weights. At least one prompt is required.
CLIP guidance presets for text-to-image generation.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DREAMSTUDIO_LIST_ENGINESList all available DreamStudio/Stability AI engines accessible with your API key. This action retrieves all AI models (engines) you can use for image generation and other tasks. Common engines include Stable Diffusion XL and various Stable Diffusion versions. Use this action to: - Discover which engines are available to your account - Get engine IDs needed for image generation requests - Check engine types and capabilities No parameters required - simply call to get the complete list of accessible engines. Using an unsupported engine_id in generation requests will cause failures; engines also vary in supported image sizes (typically capped near 1024x1024) and quality for specific tasks.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DREAMSTUDIO_USER_ACCOUNTRetrieves authenticated user's account information from Stability AI. Returns user ID, email, organization memberships, and profile picture. No parameters required - uses authenticated session.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
DREAMSTUDIO_USER_BALANCERetrieves the user's current credit balance from their DreamStudio account. Use this tool to check how many credits are available before generating images or to monitor remaining credits after API operations. Credits are consumed when generating images through the Stability AI API. For large or high-resolution batch generation, verify sufficient balance first — insufficient credits will cause failures mid-run.
Output
Data from the action execution
Error if any occurred during the execution of the action
Whether or not the action execution was successful or not
No publicly available marketplace agent is found using this tool yet. There are 87 agents privately built on Nagent that already use Dreamstudio.
Build on Nagent
Connect Dreamstudio to any Nagent agent in minutes — no API key management, no boilerplate. Just configure and deploy.
The five questions agent builders ask before adopting a new integration.
Open the External Integrations panel inside Nagent (app.nagent.ai/externalIntegration), find Dreamstudio, and click "Connect Now." You'll authenticate with an API key — Nagent handles credential storage and refresh automatically. Once connected, Dreamstudio is available to any agent in your workspace.
No. Nagent provides no-code integration for every tool. Once Dreamstudio is connected, you configure its 5 actions directly in the agent builder UI — no API calls, no boilerplate, no schema management.
Helix — Nagent's agentic agent builder — lets you drop Dreamstudio steps into any workflow visually. Pick an action (e.g., one of those listed above), fill in the inputs (Helix knows the required vs. optional schema for each parameter), and connect it to upstream/downstream steps. Triggers run as the entry point of an agent, so when a Dreamstudio event fires, the agent kicks off automatically.
Every Dreamstudio action and trigger ships with a fully-typed schema — input parameters with name, type, required flag, and description, plus the output payload shape. The schemas are documented in the sections above. Helix uses these schemas to validate your configuration at build time and to type-check the data flowing between steps.
Yes. While Dreamstudio ships with 5 pre-built artificial intelligence actions, you can layer custom logic around them inside Helix — pre/post-processing steps, conditional branches, retries, or stitching Dreamstudio together with other connected tools. For deeper customization, talk to our team about Nagent's Agentic AI Lab — forward-deployed engineers who build Dreamstudio-based workflows tailored to your business.