Skip to content
Reduced motion is on. Play a preview to watch it.
Explore models

Image

Realistic Vision

Generate a photograph-like scene with Realistic Vision.

  • Text to image
Create with Realistic Vision
Preview for Realistic Vision

Catalog preview for Realistic Vision. Review your own result before publishing.

A starting point.

Describe a specific lighting setup, camera viewpoint and subject rather than relying on a quality label.

Before you publish.

Inspect skin, hands, reflections and contact shadows at full size.

Review the quote before running. A failed generation releases its reserved credits. Download the results you want to keep; stored media is retained for 30 days.

How credits work · Use the API · Content guidelines

Settings and model questionsCheck the available settings and guidance when preparing your input.

Inputs and settings

Provide prompt and optional negative_prompt. Start with num_images=1; guidance_scale is 0–20 and num_inference_steps is 1–70.

format selects jpeg or png. Keep seed when comparing lighting changes; expand_prompt can add detail, while loras and embeddings are optional advanced inputs.

Inputs, all modes and APIModel IDs, current input limits and the API generation workflow.

Supported inputs

These fields come from the current studio form for realistic-vision. Other modes may require different inputs.

Input types, requirements and limits for realistic-vision
InputTypeRequirementOptions and limits
promptTextRequired—
embeddingsListOptional—
enable_safety_checkerOn/offOptional—
expand_promptOn/offOptional—
formatTextOptionaljpeg, png
guidance_scaleNumberOptional≥ 0 · ≤ 20
lorasListOptional—
negative_promptTextOptional—
num_imagesWhole numberOptional≥ 1 · ≤ 8
num_inference_stepsWhole numberOptional≥ 1 · ≤ 70
request_idTextOptional—
safety_checker_versionTextOptional—
seedWhole numberOptional—

Check the full model schema for all options and cross-field rules. Request a quote for your selected settings before generating.

Use Realistic Vision through the API.

Start with this model ID for the endpoint featured on this page:

realistic-vision

Input requirements belong to this model ID. Check a different mode’s schema separately when switching modes.

Check the current model schema for supported inputs and options. Other tasks may use different model IDs.

From quote to result.

Request a credit quote for your input and settings before submitting a generation. A sample output or the price of another model is not a quote for your request.

Follow the generation workflow, then poll the job for its status and result. The API and studio use the same balance.