KinoGenie
Start for free
All toolstext to image API open weights

Generate Images from Text with an API

Turn a prompt into one to four images with an open-weight model running on our GPUs, delivered as PNG or WebP files you can download. Run the preset directly on this page or call the same agent-ready endpoint from your product.

Run this tool View API recipe
LIVE TOOL
Run generate image
Describe the image, pick its shape and how many to render, and download the results here.
0 / 2000
Try:

Describe the subject, the light and the framing. Z-Image Turbo fast and cheap, 1k only, ignores negative prompts.

1024 × 1024 px

Z-Image Turbo is trained at 1024 px, so it renders at 1k only.

Up to 4. Each one is billed.

Z-Image Turbo runs without a guidance pass, so a negative prompt would have nothing to steer away from. Put what you want in the prompt itself, or switch to Qwen-Image when you need one.

1 image at 1k, Z-Image Turbo (Apache-2.0). Billed per image, reserved when the job is queued and refunded if the render fails.

Already have an account? Sign in

BEFORE / AFTER

See what the tool changes.

A real example: the after side is the unedited output of a KinoGenie job. Run the live form above to generate the same result from your own media.

BeforeSource video
WebM · VP9
mountain.webm
AfterCompatible MP4
Ready
MP4 · H.264
mountain.mp4

Demo footage: public-domain timelapses (Bureau of Land Management, Oregon · NASA SVS). Processed by the same pipeline the API and MCP tools call.

Useful defaults, typed options.

The tool slug stays stable while your agent supplies named media inputs and a narrow set of documented options.

  • Open-weight models, no GPU of your own
  • Up to four images per call, billed per image
  • Same API, MCP server and account as the video tools
What this preset does
  1. 01Send a prompt and pick a model, aspect ratio and size
  2. 02Render one to four images on a GPU worker
  3. 03Mark each file as AI-generated in its metadata
  4. 04Return one downloadable file per image in result.outputs
Stable endpointPOST /api/v1/tools/generate-image
Live API request
{
  "inputs": [],
  "options": { "prompt": "A neon-lit ramen stall in the rain at night, steam rising off the bowl, shallow depth of field, cinematic.", "aspect_ratio": "16:9", "images": 4 }
}
Successful output example
{
  "result": {
    "output": {
      "filename": "generate-image-output.mp4",
      "contentType": "video/mp4",
      "byteSize": 437021,
      "downloadUrl": "https://cdn.kinopipe.com/…"
    }
  }
}

Know the boundaries before you run.

Models: Z-Image Turbo (default, fast, 1k only) and Qwen-Image (slower, renders legible text, up to 2k)
Aspect ratios 1:1, 16:9, 9:16, 4:3, 3:4, 3:2 and 2:3, at the 1k or 2k tier; dimensions are derived server-side at a constant megapixel budget
One to four images per call, each one billed
Output is PNG by default, WebP on request; every image is returned in result.outputs, not result.output
Every image carries a synthetic-content marker in its metadata, which is our obligation as the deployer under the EU AI Act (art. 50)

About generate images

Which models can I call?

Z-Image Turbo (Apache-2.0) by default, and Qwen-Image (Apache-2.0) when you need legible text in the image or a negative prompt. Pass model to choose, or call the model page directly, which pins it for you.

How are several images returned?

One file per image in result.outputs, each with its own download URL. The video tools return a single result.output, so an agent reading both should check outputs first.

What sizes can I ask for?

Seven aspect ratios at two tiers, 1k and 2k. Dimensions are derived on a 64 pixel grid at a constant megapixel budget, so 16:9 and 1:1 cost the same at the same tier. Z-Image Turbo is 1k only.

How is it billed?

Per image, at a rate that depends on the model and the size tier. The price is reserved when the job is queued, never changes with render time, and is refunded in full if the render fails.

Related media tools

Z-Image Turbo API: Fast Text to Image

Call Z-Image Turbo, the distilled six-billion-parameter text-to-image model from Alibaba Tongyi, over a hosted API: a prompt in, up to four images out, no GPU of your own.

Explore

Qwen-Image API: Text to Image with Legible Text

Call Qwen-Image, the twenty-billion-parameter text-to-image model from Alibaba, over a hosted API. It is the one to reach for when the image itself has to contain readable words.

Explore

Generate AI Video from Text with an API

Turn a text prompt, or an image to animate, into a short video clip with native stereo audio, delivered as an MP4.

Explore