28 Services from stablestudio.io

Generates a video from a text prompt using the WAN-2.6 model, returning a job ID for async retrieval

Generates a single AI image from a text prompt using GPT-Image-1.5, with configurable resolution, aspect ratio, format, and safety tolerance, billed per generation.

Generates a video from a text prompt using the Seedance T2V model, returning a job ID for async retrieval

Generates a single AI image from a text prompt with configurable resolution, aspect ratio, format, and quality, returning an async job ID

Edits or modifies an existing image using the Flux 2 Max model via pay-per-generation AI image editing.

Generates AI video (via Sora 2 Pro model) from a text prompt, returning a job ID for async retrieval, billed per generation at $10 USDC.

Generates an AI video asynchronously using the Veo 3.1 model from a text prompt, returning a job ID to poll for results.

Generates a high-quality AI image using the Flux 2 Max model via a pay-per-generation API, returning a job ID for async retrieval

Converts raster images into scalable vector graphics using the Arrow 1.1 model, returning a job ID for async polling.

Generates AI images using the Flux 2 Pro model via a pay-per-generation API with no subscription required

Converts a raster image into a scalable vector graphic using the Arrow 1.1 Max AI model, returning a job ID for async polling.

Generates a new AI image using the Flux 2 Pro model with full control over resolution, aspect ratio, format, and safety tolerance, returning an async job ID.

Generates a video from a text prompt using the WAN-2.6 model, returning a job ID for async retrieval

Generates or edits AI images using the GPT-Image-1.5 model with configurable resolution, aspect ratio, and safety settings, billed per generation via x402 micropayment.

Asynchronously generates an edited AI image using the nano-banana-pro model, returning a job ID for polling the result.

Submits an image-to-video (i2v) generation job using the Seedance model, returning a job ID for async polling

Generates a single AI image from a text prompt using the nano-banana-pro model, returning a job ID for async retrieval

Generates a video asynchronously using the Veo 3.1 Fast model from a text prompt, returning a job ID for status polling

Generates an AI image using the Grok model with configurable resolution, aspect ratio, format, and safety settings, returning a job ID for async retrieval.

Generates an AI image via Grok model from a text prompt, returning a job ID for async retrieval

Generates a video from a text prompt using the Seedance Fast model, returning a job ID for async retrieval.

Submits a pay-per-generation AI video creation job using a text prompt, returning a job ID for async retrieval

Generates an AI video using the Sora-2 model from a text prompt, returning a job ID for async retrieval

Submits an image-to-video generation job using the Seedance Fast model, returning a job ID for async polling

Generates an AI-edited image asynchronously via a pay-per-call model, returning a job ID to poll for the result

Generates AI images using the GPT-Image-2 model via a pay-per-generation endpoint, returning a job ID for async retrieval.

Edits or modifies an existing image using OpenAI's GPT-Image-2 model, returning a job ID for async retrieval, billed per generation with no subscription.

Requests a pre-signed upload token for submitting a file (e.g. an image) to StableStudio's Vercel Blob storage in preparation for AI image/video generation.