# Text to image OpenAI-compatible endpoint for generating images from a text prompt. PrivateMind has an OpenAI-compatible endpoint that generates an image from a text prompt. > [!TIP] > In Python, the PrivateMind SDK wraps this endpoint in one typed call: see [Image generation in the Python SDK](https://docs.privatemind.com/sdk-images.html). ## Generate an image Send a model id, a prompt and a size to `POST /v1/images/generations`. ```bash curl -s "https://api.privatemind.com/v1/images/generations" \ -H "Authorization: Bearer $PMIND_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "cosmos3-super-text2image", "prompt": "a red panda on a mossy log in a misty forest at sunrise, photorealistic", "size": "1024x1024" }' ``` - **`model`** (required): an image model id. Image models have `model_type: image-gen` in `GET /v1/models`. The alias **`t2i`** points to the text-to-image model. - **`prompt`** (required): a description of the image to generate. - **`size`** (required): the output resolution as `WIDTHxHEIGHT`, for example `1024x1024`. A missing or malformed value returns `400`. - **`n`** (default `1`): number of images to generate. - **`negative_prompt`** (optional): what to keep out of the image. - **`num_inference_steps`** (default `50`): diffusion steps. Fewer is faster; more can refine detail. - **`guidance_scale`** (default `4.0`): how strongly the image adheres to the prompt. - **`seed`** (optional): set it for reproducible output; leave it out for a random image each call. - **`response_format`** (default `b64_json`): `url` is not supported. ## Response Each image comes back as a base64-encoded PNG in `data[].b64_json`, in OpenAI's images format: ```json { "created": 1781481050, "data": [ { "b64_json": "iVBORw0KGgoAAAANSUhEUgAA..." } ] } ``` Decode it to a file: ```python import base64, json, requests, os resp = requests.post( "https://api.privatemind.com/v1/images/generations", headers={"Authorization": f"Bearer {os.environ['PMIND_KEY']}"}, json={ "model": "cosmos3-super-text2image", "prompt": "a red panda on a mossy log in a misty forest at sunrise, photorealistic", "size": "1024x1024", }, timeout=300, ) resp.raise_for_status() img = base64.b64decode(resp.json()["data"][0]["b64_json"]) open("out.png", "wb").write(img) ``` > [!NOTE] > Generation is synchronous: the request stays open until the image is ready. One 1024x1024 image usually takes a few seconds. More steps or a larger size take longer, so set a generous client timeout. ## Content safety Image models may apply a content-safety guardrail, which classifies unsafe content and blurs faces, before returning results. A prompt or image flagged as unsafe is rejected with an error. ## Where next - [Models](https://docs.privatemind.com/models.html) to list image-capable models in your org. - [Authentication](https://docs.privatemind.com/authentication.html) for issuing and using API keys. - [Rate limits](https://docs.privatemind.com/rate-limits.html) for budget and RPM behaviour. - [Errors](https://docs.privatemind.com/errors.html) for status codes and error shapes.